The DOI matches its Crossref record; 69 of the 78 references it cites were found in a registry or an index; 13 of the 34 sources its claims cite were checked for support.
WoodScape: A Multi-Task, Multi-Camera Fisheye Dataset for Autonomous Driving
Open accessAbstract
Fisheye cameras are commonly employed for obtaining a large field of view in surveillance, augmented reality and in particular automotive applications. In spite of their prevalence, there are few public datasets for detailed evaluation of computer vision algorithms on fisheye images. We release the first extensive fisheye automotive dataset, WoodScape, named after Robert Wood who invented the fisheye camera in 1906. WoodScape comprises of four surround view cameras and nine tasks including segmentation, depth estimation, 3D bounding box detection and soiling detection. Semantic annotation of 40 classes at the instance level is provided for over 10,000 images and annotation for other tasks are provided for over 100,000 images. With WoodScape, we would like to encourage the community to adapt computer vision models for fisheye camera instead of using naive rectification.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
WoodScape is introduced as a multi-task, multi-camera fisheye dataset for autonomous driving, with four 190° horizontal-FOV cameras, LiDAR, GNSS/IMU, and annotations for nine tasks. It provides baseline results across segmentation, detection, depth, motion, soiling, odometry/SLAM, and 3D boxes, while arguing for native fisheye models rather than undistortion.
Key findings
- The dataset contains over 10,000 images with instance-level semantic annotation, four 1MPx RGB fisheye cameras covering 360°, one Velodyne HDL-64E LiDAR at 20 Hz, GNSS/IMU, and labels for nine tasks including semantic segmentation, 2D/3D detection, depth, motion segmentation, soiling detection, visual odometry/SLAM, and end-to-end driving.
- Baseline results include ENet segmentation IoU 51.4, Faster R-CNN 2D detection mAP 31 at IoU ≥ 0.5, ResNet10 soiling category precision 84.5%, Eigen depth RMSE 7.7, MODNet motion segmentation IoU 45, visual odometry translation <5 mm 51% and rotation <0.1° 71%, and LSD-SLAM relocalization 61%.
- For 3D bounding box detection, Complex-YOLO trained with the proposed S_srt metric achieved AP 62.46%, AOS 88.43%, and runtime 1 ms, versus 3D-IoU training with AP 64.38%, AOS 85.60%, and runtime 95 ms, improving training time by 95×.
- A pre-trained person detector achieved mAP 12 on fisheye images versus 45 for a model trained on WoodScape, which the authors use to argue that fisheye geometry must be handled explicitly.
Methods
- The dataset was captured from three geographical locations (USA, Europe, China), with highway, urban, and parking scenarios, saloon and sports utility vehicles, and intrinsic/extrinsic calibration plus timestamp synchronization.
- Annotation covers 40 semantic classes, 5k soiling images, 10k 3D box frames, 400k depth frames, 10k motion segmentation frames, 50 video sequences with over 100k frames for VO/SLAM, 500 end-to-end driving videos, and 10k synthetic frames.
- Data splitting is 6:1:3 training/validation/testing, with five splits and task-specific stratified splits; sampling uses a wrapper method based on classifier accuracy plus a filter based on image similarity. Baselines use ENet, Faster R-CNN with ResNet101, ResNet10, Eigen, MODNet, LSD-SLAM, and Complex-YOLO.
Limitations
- The paper states that 2D bounding box detection mAP of 31 is significantly lower than on other datasets and that incorporating fisheye geometry explicitly remains an open research problem.
- The paper states that spherical models do not accurately fit fisheye lenses and that adapting CNNs to fisheye distortion is an open problem; it also notes that simultaneous annotation is provided for various tasks but with exceptions due to practical limitations of optimal dataset design.
- The paper states that more than one third of the dataset is recorded in Europe and is GDPR-sensitive due to visible faces and license plates, so it follows a license-agreement approach rather than blurring or GAN retargeting; it also states that end-to-end steering/braking is not currently mature for deployment.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
13 of 34 cited sources checked · 0 supported · 1 flagged · accuracy not yet measured
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“We run the semi-supervised approach from [33] using the model proposed by Eigen [14] as baseline on our much larger dataset and obtained an RMSE (Root Mean Square Error) value of 7.7.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.5. Monocular Depth Estimation
What the sources say
- Not checked — no full text of the sourcecites [33] source
- Disputedcites [14] sourceExperimental — accuracy not yet measured
The citation in the sentence attributes the semi-supervised approach to this source; the RMSE is presented as the citing authors’ own result. Section 2 (pp. 2–3) instead describes training a network on images paired with human steering commands to predict steering, not a semi-supervised approach to monocular depth estimation. (LLM, conf=0.86)
Checked by a reasoning model — may be wrong.
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesThe cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“| Soiling Detection | ResNet10 [20] | Category (%) | 84.5 |”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 5. Conclusions
What the sources say
- Could not verifycites [20] sourceExperimental — accuracy not yet measured
The paper’s discussion of classification methods (III. Vision Algorithm Building Blocks, p. 4) and its table of established applications (p. 5) do not report a soiling-detection result. Searches for WoodScape, ResNet10, and 84.5 found no passage supporting the attributed dataset, model, or score. (LLM, conf=0.76)
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Depending on the particular task (see Section 4, for the full list), the class imbalance may be an issue [19], therefore, task-specific splits are also provided.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > Data splitting and class balancing:
What the sources say
- Partly supportedcites [19] sourceExperimental — accuracy not yet measured
Section 5.1 (p. 12) identifies a class-imbalance problem: traffic lights occur less often than light poles, and the authors suggest better class-balancing strategies. Section 5.2 (p. 12) describes separate task benchmarks and dataset splits, but does not say those splits were provided because of class imbalance. (LLM, conf=0.84)
Strength:hedged· not yet calibratedCausal:conditional· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Partly supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“| Visual Odometry | ResNet50 [20] | Translation (<5mm) Rotation (<0.1°) | 51 71 |”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 5. Conclusions
What the sources say
- Could not verifycites [20] sourceExperimental — accuracy not yet measured
The discussion of odometry in 'Towards a generic scalable algorithm framework' (p. 6) concerns its use in segmenting moving objects, not a performance evaluation. Searches for WoodScape, ResNet50, and the claimed translation threshold and score found no passage in our copy reporting that result. (LLM, conf=0.77)
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“| Visual Odometry | ResNet50 [20] | Translation (<5mm) Rotation (<0.1°) | 51 71 |”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 5. Conclusions
What the sources say
- Could not verifycites [20] sourceExperimental — accuracy not yet measured
The Motion Estimation section (p. 3) describes tracking and matching image pixels, but reports no visual-odometry benchmark score. Searches for WoodScape, ResNet50, and the stated rotation and translation thresholds found no passage supporting the score of 71. (LLM, conf=0.76)
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Could not verify
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“First fisheye dataset comprising of over 10,000 images containing instance level semantic annotation.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 1. Introduction
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesThe paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Proposal of an efficient metric for the 3D box detection task which improves training time by 95x.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 1. Introduction
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes? Based: unclearA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Annotations are made available for nine tasks, notably 3D object detection, depth estimation (overlaid on front camera) and semantic segmentation as illustrated here.”
- Also stated in: § 3.2. Dataset Acquisition · plain
“Our WoodScape dataset provides labels for several autonomous driving tasks including semantic segmentation, monocular depth estimation, object detection (2D & 3D bounding boxes), visual odometry, visual SLAM, motion segmentation, soiling detection and end-to-end driving (driving controls).”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > Abstract
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Also stated in: § 3.2. Dataset Acquisition · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our model is based on a fourth order polynomial mapping incident angle to image radius in pixels (r(θ) = a 1 θ + a 2 θ 2 + a 3 θ 3 + a 4 θ 4 ).”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2.1. Fisheye Camera Models
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesThe paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“We have designed our dataset so that simultaneous annotation is provided for various tasks with some exceptions due to practical limitations of optimal dataset design for each task.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.1. High-Level Goals
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
- It may state two separate claims as one. 36
- Probably not a substantial claim. 19
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“There are very few public fisheye datasets and none of them provide semantic segmentation annotation.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.1. High-Level Goals
What the sources say
- Could not verifycites [7] sourceExperimental — accuracy not yet measured
The RobotCar Platform (p. 1) describes fisheye cameras, and the paper says the dataset is available for download. But the Introduction (p. 1) does not assess how many public fisheye datasets exist, and searches for semantic-segmentation annotations found no passage saying that none provide them. (LLM, conf=0.72)
- Not checked — no full text of the sourcecites [9] source
- Not matchedcites [37]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“In the recent EuroCity persons dataset [5], the authors argued that any anonymization measure will introduce a bias.Thus they released their dataset with original data and a license agreement which enforces the user to strictly adhere to GDPR.We will follow a similar approach.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > GDPR challenges:
What the sources say
- Could not verifycites [5] sourceExperimental — accuracy not yet measured
Split into 2 atoms — 0 confirmed, 0 partially supported, 0 disputed, 0 misattributed, 2 unverifiable. Expand the claim to see per-atom verdicts.
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Bojarski et al. demonstrated end-to-end learning [2] for steering and recently it was applied to fisheye cameras [54].”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.9. End-to-End Steering/Braking
What the sources say
- Not checked — no full text of the sourcecites [2] source
- Could not verifycites [54] sourceExperimental — accuracy not yet measured
The Abstract and Introduction discuss semantic segmentation, but neither addresses end-to-end steering with fisheye cameras. Searches for fisheye steering and Bojarski found no relevant passage in our copy. (LLM, conf=0.76)
Strength:boosted· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“There are several popular synthetic datasets like SYNTHIA [44] and CARLA [13].”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.8. Synthetic Data Domain Transfer
What the sources say
- Could not verifycites [44] sourceExperimental — accuracy not yet measured
The citation is attached to SYNTHIA, but the passages from “Selecting Representative Data Sets” (page unavailable) discuss representative-set selection and SMOTE synthetic instances, not SYNTHIA. Searches for SYNTHIA and CARLA found no passage identifying either dataset or addressing its popularity. (LLM, conf=0.76)
- Not matchedcites [13]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Semantic segmentation networks for autonomous driving [47] have been successfully trained directly on fisheye images in [12,45].Due to absence of fisheye datasets, they make use of artificially warped images of Cityscapes for training and testing was performed on fisheye images.However, the artificial images cannot increase the originally captured FOV.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.1. Semantic Segmentation
What the sources say
- Could not verifycites [47] sourceExperimental — accuracy not yet measured
Split into 2 atoms — 0 confirmed, 0 partially supported, 0 disputed, 0 misattributed, 2 unverifiable. Expand the claim to see per-atom verdicts.
- Not checked — no full text of the sourcecites [12] source
- Not checked — no full text of the sourcecites [45] source
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Rests on an assumption: Artificially warped images cannot increase the originally captured field of view.
- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“This has been explored in [49,57,48] for narrow angle cameras.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.6. Motion Segmentation
What the sources say
- Not matchedcites [49]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [57]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Could not verifycites [48] sourceExperimental — accuracy not yet measured
The Introduction (p. 1) describes semantic segmentation for automated driving, and the Auxiliary Task Learning section (p. 3) illustrates optical flow as a possible task. Searches for motion segmentation and narrow-angle cameras found no passage saying this paper explored motion segmentation with such cameras. (LLM, conf=0.73)
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“The dataset supports correct hypothesis evaluation [55], therefore multiple splits are provided (5 in total).”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > Data splitting and class balancing:
What the sources say
- Could not verifycites [55] sourceExperimental — accuracy not yet measured
The section on large annotated datasets discusses CamVid, Cityscapes and other datasets, but not WoodScape. The benchmarking section describes an evaluation on CamVid; neither it nor the other passages found addresses WoodScape’s support for hypothesis evaluation or its five splits (searched: WoodScape, hypothesis evaluation, dataset splits). (LLM, conf=0.76)
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“In general, 3D IoU [18] is used to evaluate 3D bounding box predictions”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.4. 3D Bounding Box Detection
What the sources say
- Could not verifycites [18] sourceExperimental — accuracy not yet measured
Section 4.6, “A note on accuracy” (p. 11), discusses detection and localisation accuracy for automated parking, but does not identify 3D IoU as an evaluation metric. Searches for 3D IoU, intersection over union, and bounding-box evaluation found no passage addressing the claim. (LLM, conf=0.78)
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
- Could not verify
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In our experience, higher orders provide no additional accuracy.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2.1. Fisheye Camera Models
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In WoodScape, we provide model parameters for a more generic fisheye intrinsic calibration that is independent of any specific projection model, and does not require the added step of distortion correction.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2.1. Fisheye Camera Models
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Introduction of a novel soiling detection task and release of first dataset of its kind.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 1. Introduction
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It contains four cameras covering 360 ° accompanied by a HD laser scanner, IMU and GNSS.”
- Also stated in: § 1. Introduction · plain
“WoodScape is a comprehensive dataset for 360 ° sensing around a vehicle using the four fisheye cameras shown in Figure 2.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > Abstract
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Also stated in: § 1. Introduction · plain
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Four-camera nine-task dataset designed to encourage unified multi-task and multi-camera models.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 1. Introduction
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The plot indicates that the difference to the original fourth order polynomial is about four pixels for UCM and one pixel for eUCM for low incident angles.For larger incident angles, these models are less precise.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2.1. Fisheye Camera Models
Strength:hedged· not yet calibratedCausal:correlational· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“We introduce WoodScape, the first fisheye image dataset dedicated to autonomous driving.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > Abstract
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While the majority of data was obtained from saloon vehicles there is a significant subset from a sports utility vehicle ensuring a strong mix in sensor mechanical configurations.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.2. Dataset Acquisition
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“More than one third of our dataset is recorded in Europe and is therefore GDPR sensitive due to visible faces of pedestrians and license plates.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > GDPR challenges:
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Driving scenarios are divided across the highway, urban driving and parking use cases.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.2. Dataset Acquisition
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The video sequences can also be used for Visual SLAM where we focus on relocalization of a mapped trajectory and the metric is same as VO.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.7. Visual Odometry/SLAM
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Even though this comparison uses 3D-IoU, we achieve similar performance for average precision (3D-IoU), with better angle orientation similarity (AOS) and much faster computation time.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.4. 3D Bounding Box Detection
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The dataset also provides a set of synthetic data using accurate models of the real cameras, enabling investigations of additional tasks.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.2. Dataset Acquisition
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Thus we have added end-to-end steering and braking tasks to encourage modular end-to-end architectures and to explore optimized perception for the control task.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.9. End-to-End Steering/Braking
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We provide 50 video sequences comprising of over 100k frames with ground truth.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.7. Visual Odometry/SLAM
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Images are provided at 1MPx 24-bit resolution and videos are uncompressed at 30fps ranging in duration from 30s to 120s.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.2. Dataset Acquisition
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“• 4x 1MPx RGB fisheye cameras (190 • horizontal FOV) • 1x LiDAR rotating at 20Hz (Velodyne HDL-64E) • 1x GNSS/IMU (NovAtel Propak6 & SPAN-IGM-A1) • 1x GNSS Positioning with SPS (Garmin 18x) • Odometry signals from the vehicle bus.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.2. Dataset Acquisition
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Intrinsic and extrinsic calibrations are provided for all sensors as well as timestamp files to allow synchronization of the data.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.2. Dataset Acquisition
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“| Segmentation | Classes Frames | 8 400 | 30 5k | 66 25k | -- | 25 140k | 40 5.7k | 40 10k |”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 5. Conclusions
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“We achieve a mAP score of 31 which is significantly less than the accuracy achieved in other datasets.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.2. 2D Bounding Box Detection
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“We also provide previous and next images for exploring multi-stream models like MOD-Net [49].”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.6. Motion Segmentation
What the sources say
- Not checked — no full text of the sourcecites [49] source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In addition to providing fisheye data, we provide data for many more tasks than is typical (nine in total), providing completely novel tasks such as soiled lens detection.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.2. Dataset Acquisition
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“3D box annotation is provided for 10k frames with 3 classes namely 'pedestrian', 'vehicle' and 'cyclist'.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.4. 3D Bounding Box Detection
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We provide more than 100k images of all four cameras (totaling 400k) using ground truth provided by LiDAR.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.5. Monocular Depth Estimation
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“| 2D Bounding Box 1 | Classes Frames | 3 15k | -- | -- | -- | -- | 10 5.7k | 7 10k |”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 5. Conclusions
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
In the paper
“Fisheye is particularly beneficial to automotive low speed manoeuvring scenarios such as parking [21] where accurate full coverage near field sensing can be achieved with just four cameras.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.1. High-Level Goals
What the sources say
- Not matchedcites [21]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Not matched
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“However, spherical models do not provide an accurate fit for fisheye lenses and it is an open problem.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2.2. Image Undistortion vs. Model Adaptation
What the sources say
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Because of fundamental limitations of undistortion, an alternate approach of adapting the algorithm incorporating fisheye model discussed in previous section could be an optimal solution.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2.2. Image Undistortion vs. Model Adaptation
Tests✓ Asserted: passes✗ Checkable: fails✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may be too vague to check against evidence.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This advantage comes with some drawbacks in the significantly more complex projection geometry that fisheye cameras exhibit.That is, images from fisheye cameras display severe distortion.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2. Overview of Fisheye Camera Projections
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Firstly, the FOV is greater than 180 • , hence there are rays incident from behind the camera and it is not possible to establish a complete mapping to a rectilinear viewport.This leads to a loss of FOV, this is seen via the missing yellow pillars in the corrected image.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2.2. Image Undistortion vs. Model Adaptation
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Given their extremely wide field of view, they can observe the full surrounding of a vehicle with a minimal number of sensors, with just four cameras typi- cally being required for full 360 • coverage (Figure 2).”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2. Overview of Fisheye Camera Projections
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Standard computer vision models do not generalize easily to fisheye cameras because of large non-linear distortion.For example, translation invariance is lost for a standard convolutional neural net (CNN).”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 2.2. Image Undistortion vs. Model Adaptation
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Existing datasets are primarily designed to facilitate task-specific learning and they don't provide simultaneous annotation for all the tasks.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.1. High-Level Goals
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes? Based: unclearIt may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Full control of the splitting mechanism is provided allowing for each class to be represented equally within each split (i.e.stratified sampling).”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > Data splitting and class balancing:
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Unlike the front camera which is behind the windshield, the surround view cameras are usually directly exposed to the adverse environmental conditions, and thus prone to becoming soiled or water drops forming on the lens.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.3. Camera Soiling Detection
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The classes to detect are {opaque, transparent}.Typically, opaque soiling arises from mud and dust (Figure 8 right image), and transparent soiling arises from water and ice (Figure 8 left image).However, in practice it is common to see water producing”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.3. Camera Soiling Detection
Strength:plain· not yet calibratedCausal:correlational· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Rests on an assumption: Opaque soiling typically arises from mud and dust, and transparent soiling from water and ice.
- Rests on an assumption: Water can produce 'opaque' regions in the camera image.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“High-quality data is ensured via quality checks at all stages of the data collection process.Annotation data undergoes a rigorous quality assurance by highly skilled reviewers.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.2. Dataset Acquisition
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We observe that it is necessary to incorporate the fisheye geometry explicitly, which is an open research problem.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.2. 2D Bounding Box Detection
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Collecting frames at a frame rate of 30fps, particularly at low speeds, ultimately leads to significant image overlap, therefore, having an effective sampling strategy to distill the dataset is critical.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > Sampling strategy:
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“The task of soiling detection was to our best knowledge first defined in [56].”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.3. Camera Soiling Detection
What the sources say
- Not checked — no full text of the sourcecites [56] source
Strength:hedged· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“However, at the same time, it was shown that careful inspection of the training sets for outliers improves the robustness of deep neural networks [36], especially with regards to the adversarial examples.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 3.3. Dataset Design
What the sources say
- Not checked — no full text of the sourcecites [36] source
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
In the paper
“Visual Odometry (VO) is necessary for creating a map from the objects detected [38].”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > 4.7. Visual Odometry/SLAM
What the sources say
- Not checked — no full text of the sourcecites [38] source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
The paper relies on this without support.
Surround view systems have at least four cameras rigidly connected to the body of the car.
“Surround view systems have at least four cameras rigidly connected to the body of the car.”
The paper relies on this without support.
Artificially warped images cannot increase the originally captured field of view.
“However, the artificial images cannot increase the originally captured FOV.”
The paper relies on this without support.
Opaque soiling typically arises from mud and dust, and transparent soiling from water and ice.
“Typically, opaque soiling arises from mud and dust (Figure 8 right image), and transparent soiling arises from water and ice (Figure 8 left image).”
The paper relies on this without support.
Water can produce 'opaque' regions in the camera image.
“However, in practice it is common to see water producing”
The paper relies on this without support.
3D IoU has drawbacks, especially for rotated objects.
“In general, 3D IoU [18] is used to evaluate 3D bounding box predictions, but there are drawbacks, especially for rotated objects.”
The paper relies on this without support.
Two boxes can reach a good 3D IoU score while overlapping in total with an opposite heading.
“Two boxes can reach a good 3D IoU score, while overlapping in total with an opposite heading.”
The paper relies on this without support.
Exact calculation in 3D space is time-consuming.
“Additionally, an exact calculation in 3D space is a time consuming task.”
The paper relies on this without support.
Motion is a strong cue in automotive due to ego-motion of cameras and dynamic objects are critical interacting agents.
“In automotive, motion is a strong cue due to ego-motion of the cameras on the moving vehicle and dynamic objects around the vehicle are the critical interacting agents.”
The paper relies on this without support.
Synthetic data is crucial for autonomous driving.
“Synthetic data is crucial for autonomous driving for many reasons.”
The paper relies on this without support.
There are legal restrictions like recording videos of a child.
“Secondly, there are legal restrictions like recording videos of a child.”
The paper relies on this without support.
Synthetic data is the only way to obtain dense depth and optical flow annotation.
“Finally, synthetic data is the only way to obtain dense depth and optical flow annotation.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Other works explored image restoration using inpainting or generative methods [3,4], though such approaches carry risks of hallucinated visual cues that may mislead the perception system.”
From AI-Based Image Quality and Lens Defect Analysis in Autonomous Driving: A Framework with U-Net-Based Soiling Detection (2025) · cites this paper as [4]
Experimental — accuracy not yet measured
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 3×
“7 Motion Segmentation MODNet [49] IoU 45 Visual Odometry ResNet50 [20] Translation (<5mm) 51 Rotation (<0.”
BackgroundMethodAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“We fine-tune their model for our dataset by training with categorical cross entropy loss and Adam [29] optimizer.”
MethodFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812 · cited 3×
“4 2D Bounding Box Faster R-CNN [43] mAP (IoU>0.”
BackgroundMethodImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“We initialize the network with ImageNet [11] pre-trained weights.”
MethodThe pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599
Are we ready for autonomous driving? The KITTI vision benchmark suite
Geiger, A., Lenz, P., & Urtasun, R. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248074 · Cited by 14,897 · cited 12×
“Performance of 2D object detection is reported in terms of mean average precision (mAP) when IoU≥ 0.5 between predicted and ground truth bounding boxes.”
BackgroundMethodInfluentialThe Cityscapes Dataset for Semantic Urban Scene Understanding
Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.350 · Cited by 12,433 · cited 4×
“Task/Info Quantity KITTI [17] Cityscapes [10] Mapillary [39] nuScenes [6] ApolloScape [24] BDD100k [59] WoodScape Ours”
BackgroundMethodInfluentialA Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714 · cited 1×
“the desired precision. Another, more appropriate, approach is to exchange these regions by some automatically generated proposals. For example, exchanging all faces for automatically generated ones2 [25]. Such anonymized data will not violate GDPR rules as the original person is no longer identifiable. We aim to ensure…”
BackgroundVision meets robotics: The KITTI dataset
Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913491297 · Cited by 9,913 · cited 3×
“Task/Info Quantity KITTI [17] Cityscapes [10] Mapillary [39] nuScenes [6] ApolloScape [24] BDD100k [59] WoodScape Ours”
Background
Flagged first, then by citations
9 of the 78 references couldn’t be matched to a known paper.
Research works printed but not linked: 2
- kumar, 2018, Near-field depth estimation using monocular fisheye camera: A semi-supervised learning approach using sparse LiDAR data, CVPR Workshop
- caruso, 2015, Largescale direct SLAM for omnidirectional cameras, Proceedinsg of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 141
Cited by
Sorted by citations
Items 101–200 of 300
Gaussian Label Distribution Learning for Spherical Image Object Detection
Xu, H., Liu, X., Zhao, Q., et al. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00106 · Cited by 11
“In the past few years, with the numerous development of panoramic cameras with omnidirectional vision, the applications of spherical images and videos are also becoming more extensive, such as virtual & augmented reality [9,17,24], robotics [7,8,18], automatic driving [1,28,31], etc.”
BackgroundF2BEV: Bird's Eye View Generation from Surround-View Fisheye Camera Images for Automated Driving
Samani, E. U., Tao, F., Dasari, H. R., Ding, S., & Banerjee, A. G. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10341862 · Cited by 14
“We believe distortion-aware attention modules based on other projection models [37], [42]–[44] can also be incorporated into standard BEV generation methods designed for PV images to achieve better performance than image undistortion-based approaches.”
Context-Aware Multi-Task Learning for Traffic Scene Recognition in Autonomous Vehicles
Lee, Y., Jeon, J., Yu, J., & Jeon, M. (2020) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv47402.2020.9304708 · Cited by 10
“Existing deep learning-based MTL methods in computer vision [10], [36]–[41] demonstrated the efficiency, highlighting the extensibility for future developments and applications.”
MethodPublic Life in Public Space (PLPS): A multi-task, multi-group video dataset for public life research
Qing, L., Li, L., Xu, S., Huang, Y., Liu, M., Jin, R., Лю, Б., Niu, T., Wen, H., Wang, Y., et al. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00404 · Cited by 12
“For example, WoodScape [43] was released with original data and a license agreement which enforces the users to strictly ad-3619 (3) Dazhou (1) Liupanshui (6) Zunyi (2) Xuchang (4) Jinchang (3) Qianjiang (1) Chuxiong (1) Table 2.”
MethodBillings, G., & Johnson-Roberson, M. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2994036 · Cited by 12
“Some recent work seeks to address this lack of annotated fisheye datasets [35], [36].”
BackgroundCompact Meta‐Camera for Intelligent Wide‐Angle and Low‐Light Imaging
Hao, C., Wu, Y., Yuan, Z., et al. (2025) · Laser & Photonics Review · doi:10.1002/lpor.202500803 · Cited by 10
AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration
Tirado-Garín, J., & Civera, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00754 · Cited by 15
“1, where we also indicate the currently implemented models, but our formulation can also be applied to others, e.g . the WoodScape model [97] or the ones proposed by Scaramuzza et al. [70] and Urban et al. [84].”
Challenges of Indoor SLAM: A Multi-Modal Multi-Floor Dataset for SLAM Evaluation
Kaveti, P., Gupta, A., Giaya, D., Karp, M., Keil, C., Nir, J. S., Zhang, Z., & Singh, H. (2023) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case56687.2023.10260618 · Cited by 10
Monocular Depth Estimation from a Fisheye Camera Based on Knowledge Distillation
Son, E., Choi, J., Song, J., et al. (2023) · Sensors · doi:10.3390/s23249866 · Cited by 10
“On the other hand, the WoodScape dataset [3] provides surrounding fisheye camera images, which were captured by four fisheye cameras.”
BackgroundMethodLin, H., Parsi, A., Mullins, D., Horgan, J., Ward, E., Eising, C., Denny, P., Deegan, B. M., Glavin, M., & Jones, E. (2024) · Journal of Imaging · doi:10.3390/jimaging10070153 · Cited by 13
Self-citationThe Role of AI in Smart Mobility: A Comprehensive Survey
Coco, M. D., Carcagnì, P., Trilles, S., Iskandaryan, D., & Leo, M. (2025) · Electronics · doi:10.3390/electronics14091801 · Cited by 12
Yun, H., & Park, D. (2022) · Sensors · doi:10.3390/s22228890 · Cited by 10
“Various types of sensors are used to receive data, among which camera sensors and methods for processing visual information input are active fields of research [3,4].”
BackgroundDarSwin: Distortion Aware Radial Swin Transformer
Athwale, A., Afrasiyabi, A., Lagüe, J., et al. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00545 · Cited by 9
HEAL-SWIN: A Vision Transformer on the Sphere
Carlsson, O., Gerken, J. E., Linander, H., Spieß, H., Ohlsson, F., Petersson, C., & Persson, D. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00580 · Cited by 16
“In the spiral shifting, they occur at the pole and at the boundary of the half sphere covered by the grid.”
BackgroundPanorAMS: Automatic Annotation for Detecting Objects in Urban Context
Groenen, I., Rudinac, S., & Worring, M. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3279696 · Cited by 12
“The WoodScape [27] dataset concerns images of a similarly large horizontal field of view, but a different type of distortion.”
BackgroundCamera calibration for the surround-view system: a benchmark and dataset
Qin, L., Lin, C., Huang, S., et al. (2024) · The Visual Computer · doi:10.1007/s00371-024-03275-9 · Cited by 9
“The Woodscape dataset[31] is the first fisheye dataset that includes about 10,000 images with instance-level semantic annotation.”
FisheyeSuperPoint: Keypoint Detection and Description Network for Fisheye Images
Konrad, A., Eising, C., Sistu, G., McDonald, J., Villing, R. C., & Yogamani, S. K. (2022) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0010795400003124 · Cited by 10
“In our case, we use a radial polynomial function for π , as per (Yogamani et al., 2019): where p ( θ ) is a polynomial of order n , with n = 4 typically sufficient.”
MethodSelf-citationParkScape: A Large-Scale Fisheye Dataset for Parking Slot Detection and a Benchmark Method
Fu, L., Ma, D., Qu, X., Jiang, X., Shan, L., & Zeng, D. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3406840 · Cited by 8
“From the visualization, we observe that our distribution is similar to that of the autonomous driving fisheye image dataset WoodScape [40], both exhibiting dense distributions along curves.”
BackgroundMethodAlmin, A., Lemarié, L., Duong, A. K., & Kiran, B. R. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3290516 · Cited by 9
An adversarial pedestrian detection model based on virtual fisheye image training
Zhang, J., & Dou, J. F. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-024-03018-2 · Cited by 8
Techniques for detecting and masking faults in semantic segmentation applications
Burel, S., Evans, A., & Anghel, L. (2024) · Microelectronics Reliability · doi:10.1016/j.microrel.2024.115397 · Cited by 8
A Dataset of Annotated Omnidirectional Videos for Distancing Applications
Mazzola, G., Presti, L. L., Ardizzone, E., & Cascia, M. L. (2021) · Journal of Imaging · doi:10.3390/jimaging7080158 · Cited by 10
“[19], is a dataset for 360◦ sensing around a vehicle using four fisheye cameras (each with a 190◦ horizontal FOV).”
Kim, S., & Park, S.-Y. (2022) · Applied Sciences · doi:10.3390/app12052403 · Cited by 8
FisheyePixPro: Self-supervised pretraining using Fisheye images for semantic segmentation
Cheke, R., Sistu, G., Eising, C., van de Ven, P., Kumar, V. R., & Yogamani, S. (2022) · Autonomous Vehicles and Machines · doi:10.2352/ei.2022.34.16.avm-147 · Cited by 11
“These fisheye images are obtained under same conditions as WoodScape [39] and it consists of around 50k unla-belled fisheye images.”
MethodSelf-citationCamera Blockage Detection in Autonomous Driving using Deep Neural Networks
Vikas, N. R., Pahwa, G., & Mohanty, S. (2022) · International Conference on Computer Science, Engineering and Applications (ICCSEA) · doi:10.1109/iccsea54677.2022.9936418 · Cited by 9
ADD: An automatic desensitization fisheye dataset for autonomous driving
Wu, Z., Chen, X., Wei, H., et al. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106766 · Cited by 8
“WoodScape[71] real fisheye image pedestrian/car 4 1280*966”
BackgroundSwin‐fisheye: Object detection for fisheye images
Zhang, D., Yang, T., & Zhao, B. (2024) · IET Image Processing · doi:10.1049/ipr2.13216 · Cited by 8
Automotive DNN-Based Object Detection in the Presence of Lens Obstruction and Video Compression
Baris, G., Li, B., Chan, P. H., Avizzano, C. A., & Donzella, V. (2025) · IEEE Access · doi:10.1109/access.2025.3544773 · Cited by 7
“The idea behind this noise model is to mimic the appearance of random mud drops on the camera lens, as shown in WoodScape dataset [41], [62], having the possibility to control several parameters (number of drops, size of each drop, fuzziness , etc.).”
Trustworthy Sensor Fusion Against Inaudible Command Attacks in Advanced Driver-Assistance Systems
Guan, J., Pan, L., Wang, C., Yu, S., Gao, L., & Zheng, X. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3275931 · Cited by 7
“Note that multiple cameras are widely used in autonomous driving perceptions, and multimodal sensor fusion is vital for a comprehensive understanding of road conditions and increasing accuracy to ensure autonomous driving [6].”
BackgroundOrdered Atomic Activity for Fine-grained Interactive Traffic Scenario Understanding
Agarwal, N., & Chen, Y. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00792 · Cited by 7
“In recent years, many traffic scene datasets have been proposed to stimulate progress in detection [20, 84, 55, 70, 26], tracking [20, 84, 55, 70, 26, 60, 59], PIE [59] JAAD [60] STIP [46] semantic segmentation [11, 84, 88, 19], trajectory forecast [26, 90, 69], and long-term localization [47].”
BackgroundJoint Deployment of Truck-Drone Systems for Camera-Based Object Monitoring
Wang, L., Wang, W., Dai, H., et al. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3367849 · Cited by 7
“Challenges in truck-drone system deployment: 1) The QoM affects the application of obtained images heavily [37], [38], [39].”
BackgroundImproving DNN Fault Tolerance in Semantic Segmentation Applications
BurelT, S., EvansT, A., & Anghel, L. (2022) · Proceedings · doi:10.1109/dft56152.2022.9962354 · Cited by 8
“Woodscape[9] is a publicly available multi-camera fish-eye data-set for autonomous driving including annotations for semantic segmentation.”
BackgroundMethodVision Control Unit in Fully Self Driving Vehicles using Xilinx MPSoC and Opensource Stack
Chakaravarthy, R. V., Kwon, H. J., & Jiang, H. L. (2021) · Asia and South Pacific Design Automation Conference (ASP-DAC) · doi:10.1145/3394885.3431616 · Cited by 8
“Fisheye and De-warped Images [6] The solution presented in this paper implements the dewarping using OpenGLES, in order to offload the compute to GPU.”
MethodThe HAInich: A multidisciplinary vision data-set for a better understanding of the forest ecosystem
Milz, S., Wäldchen, J., Abouee, A., Ravichandran, A. A., Schall, P., Hagen, C., Borer, J., Lewandowski, B., Wittich, H.-C., & Mäder, P. (2023) · Scientific Data · doi:10.1038/s41597-023-02010-8 · Cited by 7
Self-citationOmniStitch: Depth-Aware Stitching Framework for Omnidirectional Vision with Multiple Cameras
Kim, S. G., Hong, S., Park, K., et al. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681208 · Cited by 6
Ensemble-Based Semi-Supervised Learning to Improve Noisy Soiling Annotations in Autonomous Driving
Uřičář, M., Sistu, G., Yahiaoui, L., & Yogamani, S. K. (2021) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc48978.2021.9565086 · Cited by 6
“The soiling task was first formally defined in [5] based on WoodScape dataset [17].”
MethodSelf-citationExploiting the Distortion-Semantic Interaction in Fisheye Data
Kokilepersaud, K., Prabhushankar, M., Yarici, Y., AlRegib, G., & Parchami, A. (2023) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2023.3272281 · Cited by 7
“Firstly, WoodScape is the only realworld fisheye AV dataset with object bounding box labels.”
MethodInfluentialSemantic Segmentation for Autonomous Driving
Yang, J., Guo, S., Bocus, M. J., Chen, Q., & Fan, R. (2023) · Advances in computer vision and pattern recognition · doi:10.1007/978-981-99-4287-9_4 · Cited by 8
Xu, H., Zhang, X., He, J., Geng, Z., Pang, C., & Yu, Y. F. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2024.3395653 · Cited by 6
“Valeo releases the first fisheye dataset Woodscape [27], to encourage the development of native fisheye models.”
WatchPose: A View-Aware Approach for Camera Pose Data Collection in Industrial Environments
Yang, C., Simon, G., See, J., Berger, M., & Wang, W. (2020) · Sensors · doi:10.3390/s20113045 · Cited by 7
“More recently, the WoodScape [18] dataset were collected from a car”
Exploring Sensor Impact and Architectural Robustness in Adverse Weather on BEV Perception
Kumar, S., Sharma, S., Asghar, R., Mohandas, R., Brophy, T., Sistu, G., Grua, E. M., Donzella, V., & Eising, C. (2025) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2025.3621862 · Cited by 5
“Uricar et al. proposed DirtyGAN [51], which introduces synthetic soiling generation to reduce annotation effort and boost detection accuracy, supported by the WoodScape dataset [47].”
Self-citationQueryCDR: Query-Based Controllable Distortion Rectification Network for Fisheye Images
Guo, P., Liu, C., Hou, X., et al. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72633-0_15 · Cited by 5
“In addition, to further demonstrate the generalization ability of QueryCDR, we conducted experiments on real-world fisheye image datasets [57] in Fig.”
Wu, Z., Zhang, W., Wang, J., Wang, M., Gan, Y., Gou, X., Fang, M., & Song, J. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636707 · Cited by 5
Emeršič, Ž., Hrastnik, G., Peer, N. M., & Peer, P. (2023) · Računalniška obdelava slik in njena uporaba v Sloveniji (ROSUS) · doi:10.18690/um.feri.4.2023.8 · Cited by 6
Meydani, A. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-43763-2_9 · Cited by 6
Vision-based safe autonomous UAV docking with panoramic sensors
Nguyen, P. T. A., Westerlund, T., & Queralta, J. P. (2023) · Frontiers in Robotics and AI · doi:10.3389/frobt.2023.1223157 · Cited by 5
“Most noticeable is the Woodscape dataset (Yogamani et al., 2019) for autonomous driving, comprising over 100,000 images from four surrounding cameras.”
BackgroundSTRIDE: Street View-based Environmental Feature Detection and Pedestrian Collision Prediction
González, C., Ayobi, N., Escallón, F., Baldovino-Chiquillo, L., Wilches-Mogollon, M. A., Pasos, D., Ramírez, N., Pinzón, J. D., Sarmiento, O. L., Quistberg, D. A., et al. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00347 · Cited by 5
“Further approaches use data gathered with fisheye and surround-view cameras annotated for semantic scene parsing [24, 92, 29, 43, 49], thus introducing significant distortion and deformation caused by this type of cameras.”
MethodDCPB: Deformable Convolution based on the Poincaré Ball for Top-view Fisheye Cameras
Wei, X., Ran, Z., & Lu, X. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01224 · Cited by 5
“However, the geometric transformations inherent in fisheye cameras cause spatial distortion, leading to magnifying objects near the center of fisheye images while the objects away from the center of fisheye images shrink [41,46].”
BackgroundCao, H., Li, Y., Liu, Y., Li, X., Chen, G., & Knoll, A. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802087 · Cited by 5
“Extensive experiments conducted on the WoodScape [13] and MS COCO [23] datasets indicate that the proposed method strikes a favorable balance between accuracy and efficiency.”
InfluentialContinual Learning for Multi-camera Relocalisation
Cabrera-Ponce, A. A., Martin-Ortiz, M. I., & Martínez-Carranza, J. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-89817-5_22 · Cited by 5
Performance Comparison of Soiling Detection Using Anomaly Detection Methodology
Lee, J., Jeon, C.-R., & Kang, S. (2022) · International SoC Design Conference · doi:10.1109/isocc56007.2022.10031428 · Cited by 5
“According to the evaluation obtained from the official and unofficial code implementation using WoodScape dataset [2], PatchCore [6] outperformed other methods in terms of anomaly detection and segmentation.”
BackgroundMethodInfluentialSurround-View Fisheye Camera Viewpoint Augmentation for Image Semantic Segmentation
Cho, J., Lee, J., Ha, J., Resende, P., Bradaï, B., & Jo, K. (2023) · IEEE Access · doi:10.1109/access.2023.3276985 · Cited by 6
“2 shows the quantitative results of various image models [22], [23], [24], [25], [26] trained using the WoodScape dataset [7].”
BackgroundMethodInfluentialScheduling Resource to Deploy Monitors in Automated Driving Systems
Su, P., Fan, T., & Chen, D. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-37720-4_26 · Cited by 5
2.5D vehicle odometry estimation
Eising, C., Pereira, L., Horgan, J., et al. (2021) · IET Intelligent Transport Systems · doi:10.1049/itr2.12143 · Cited by 5
“This is, in fact, the same vehicle setup that is used to capture the WoodScape dataset [45].”
MethodSelf-citationFisheyeDepth: A Real Scale Self-Supervised Depth Estimation Model for Fisheye Camera
Zhao, G., Liu, Y., Qi, W., Ma, F., Liu, M., & Ma, J. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127840 · Cited by 5
“Since the self-supervised model [22], [23], [41] for fisheye images has not been open-sourced and its employed WoodScape [44] dataset does not provide ground-truth depth for fisheye images, we did not include it in our experiments.”
VM-MODNet: Vehicle Motion aware Moving Object Detection for Autonomous Driving
Rashed, H., Sallab, A. E., & Yogamani, S. K. (2021) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc48978.2021.9564662 · Cited by 4
“In [24], MOD has been explored on images captured by wide-angle fisheye camera using [25] dataset.”
MethodSelf-citationHogan, C., & Sistu, G. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-26438-2_21 · Cited by 4
Self-citationFisheyePP4AV: A Privacy-Preserving Method for Autonomous Vehicles on Fisheye Camera Images
Trinh, L., Ha, B., & Tran, A. T. (2023) · RIVF International Conference on Computing and Communication Technologies (RIVF) · doi:10.1109/rivf60135.2023.10471879 · Cited by 4
“This data consists of 244 fisheye camera images which originally provided by WoodScape [21] are well annotated both face and license plate.”
MethodImpact of Video Compression Artifacts on Fisheye Camera Visual Perception Tasks
Sakthi, M., Kerofsky, L. J., Kumar, V. R., et al. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00137 · Cited by 4
“Therefore, extending the work of Chan et al. [2] to wide FOV images, we are the first to apply the standard video compression codecs(HEVC, AVC) on wide FOV, fisheye images ([8, 34] to quantify both impact of lossy compression on Deep Learning model inference and training.”
MethodSelf-citationA Comparison of Spherical Neural Networks for Surround-View Fisheye Image Semantic Segmentation
Manzoor, A., Mohandas, R., Scanlan, A., Grua, E. M., Collins, F., Sistu, G., & Eising, C. (2025) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2025.3541891 · Cited by 5
“They evaluated their approach using the real-world Woodscape dataset [12].”
InfluentialSelf-citationConditional Stable Diffusion for Distortion Correction and Image Rectification
Kumari, P., & Das, S. (2025) · Pattern Recognition Letters · doi:10.1016/j.patrec.2025.04.033 · Cited by 4
Delgado, G., García, M., Nieto, M., de Gordoa, J. A. Í., Perez, C., Pujol, D., & Jevtić, A. (2022) · Multidimensional Signal Processing Workshop · doi:10.1109/ivmsp54334.2022.9816285 · Cited by 4
AirFisheye Dataset: A Multi-Model Fisheye Dataset for UAV Applications
Jaisawal, P. K., Papakonstantinou, S., & Gollnick, V. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611092 · Cited by 5
“If the available dataset contains fisheye images, these mostly come from car drives, such as WoodScape [14], KITTI-360 [15], SynWoodScape [16], etc.”
MethodInstance segmentation in fisheye images
Dufour, R., Meurie, C., Strauss, C., & Lézoray, O. (2020) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta50016.2020.9286623 · Cited by 7
“Recently, the WoodScape dataset [6] was proposed”
Real-Time Object Detection on Edge Devices: A Fisheye Specific DFINE
Park, J., Lee, J., & Yong, Y. (2025) · 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw69036.2025.00573 · Cited by 4
“In addition, fisheye-centric datasets such as WoodScape [38] and FishEye8K [9] cover diverse cameras and lighting conditions, more faithfully reflecting real-world traffic surveillance environments.”
DarSwin-Unet: Distortion Aware Architecture
Athwale, A., Shili, I., Bergeron, É., et al. (2025) · IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv61041.2025.00840 · Cited by 3
Two Decades of Multi-View Clustering: Taxonomy, Application, and Challenge
Liu, X., Liang, K., Wang, J., Liu, S., Wang, X., & Wang, H. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3640109 · Cited by 3
“Forinstance, several features, HOG [217], LBP [218], SIFT [219] and RGB-D [220] can be extracted from image and video.”
FlyAwareV2: A multimodal cross-domain UAV dataset for urban scene understanding
Barbato, F., Caligiuri, M., & Zanuttigh, P. (2026) · Signal Processing Image Communication · doi:10.1016/j.image.2026.117483 · Cited by 3
Guo, A., Li, Y., Huang, J., Li, B., Na, X., Lv, C., Chen, L. F., Li, L., & Wang, F. (2026) · Journal of Field Robotics · doi:10.1002/rob.70189 · Cited by 5
Distortion-Adaptive Grape Bunch Counting for Omnidirectional Images
Akai, R., Utsumi, Y., Miwa, Y., Iwamura, M., & Kise, K. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412659 · Cited by 4
A Feature-based Approach for the Recognition of Image Quality Degradation in Automotive Applications
Bauer, F. (2023) · International Conference on Systems, Signals and Image Processing · doi:10.1109/iwssip58668.2023.10180245 · Cited by 3
“Data Set 3 is the subset of the WoodScape data set that is publicly available [1].”
BackgroundFishSegSSL: A Semi-Supervised Semantic Segmentation Framework for Fish-Eye Images
Paul, S., Patterson, Z., & Bouguila, N. (2024) · Journal of Imaging · doi:10.3390/jimaging10030071 · Cited by 3
“In the rapidly evolving landscape of computer vision applications, various real-world computer vision applications (e.g., autonomous driving) are benefiting from the use of large field-of-view (FoV) cameras [1,2].”
BackgroundMethodInfluentialFisheye Object Detection with Visual Prompting-Aided Fine-Tuning
Jeon, M., Park, G.-M., & Hwang, H. (2024) · Remote Sensing · doi:10.3390/rs16122054 · Cited by 5
Toward Oriented Fisheye Object Detection: Dataset and Baseline
Yang, J., Lin, C., Nie, L., et al. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3702640 · Cited by 3
“There are some outstanding datasets for fisheye detection like Woodscape [43] including 10,000 images with 7 categories.”
PolyOculus: Simultaneous Multi-view Image-Based Novel View Synthesis
Yu, J. J., Aumentado‐Armstrong, T., Forghani, F., Derpanis, K. G., & Brubaker, M. A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73036-8_25 · Cited by 3
Liu, C., Zuo, H., Yao, J., et al. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-01870-4 · Cited by 3
Physics-directed Data Augmentation for Deep Model Transfer to Specific Sensor
Luo, W., Yan, Z., Song, Q., & Tan, R. (2022) · ACM Transactions on Sensor Networks · doi:10.1145/3549076 · Cited by 5
“Note that a fourth-order polynomial function can well represent the model of fisheye cameras, while higher orders provide no additional benefit in terms of accuracy [34].”
Background3D Human Pose Estimation in Weightless Environments Using a Fisheye Camera
Minoda, K., & Yairi, T. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9982265 · Cited by 3
“One naive approach is to undistort the fisheye images into rectilinear, but the area with a FOV larger than 180◦ cannot be reprojected [14]; thus, the approach cannot fully take advantage of the fisheye camera.”
BackgroundFisheye object detection based on standard image datasets with 24-points regression strategy
Xu, X., Gao, Y., Liang, H. Z., Yang, Y. M., & Fu, M. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981891 · Cited by 3
“For example, the number of images in WoodScape [8], a classical fisheye dataset, is less numerous than that of some standard image datasets, such as PASCAL VOC [9], Microsoft COCO [10], Open Images [11] and Objects365 [12].”
BackgroundRavi, S., Climent-Pérez, P., Morales, T., Huesca-Spairani, C., Hashemifard, K., & Flórez‐Revuelta, F. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00690 · Cited by 3
“such as the improvement of autonomous driving systems [27,32] and robotics [6].”
BackgroundPAIR360: A Paired Dataset of High-Resolution 360$^{\circ }$ Panoramic Images and LiDAR Scans
Kim, G., Kim, D., Jang, J., & Hwang, H. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3460418 · Cited by 4
“Other notable datasets incorporating multiple cameras include nuScenes [26], Oxford Robot Car [27], and WoodScape [28].”
MethodAHFS-PTP: an adaptive hybrid feature selection method for pedestrian trajectory prediction
Wang, B., Zhang, J., Zhang, H., et al. (2025) · Transportmetrica B Transport Dynamics · doi:10.1080/21680566.2025.2490549 · Cited by 3
MIPD: A Multi-Sensory Interactive Perception Dataset for Embodied Intelligent Driving
Li, Z., Zhang, T., Zhou, M., Tang, D., Zhang, P., Liu, W., Yang, Q., Shen, T., Wang, K., & Liu, H. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3593298 · Cited by 6
“In addition, the data of CAN-bus, GPS, HR Camera, Radar HDMap HRCamera Light Vibration KITTI [10] 2012 Apolloscape [14] 2016 Woodscape [15] 2019 Nuscenes [11] 2019 Waymo [12] 2019 Argoverse [13] 2019 CARRAD [16] 2020 ONCE [17] 2021 ZOD [18] 2023 Ours 2024 [10] 2012 Apolloscape [14] 2016 Woodscape…”
Planar multi-aperture fish-eye lens using metagratingPreprint
Zang, Z., Wang, H., Han, Y., Li, H., Fu, H., & Luo, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.07872 · Cited by 3
Eberhardt, T. D., Brühl, T., Schwager, R., Sohn, T. S., & Stork, W. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00507 · Cited by 2
Yogamani, S., Sistu, G., Denny, P., & Courtney, J. (2025) · Italian National Conference on Sensors · doi:10.3390/s25123735 · Cited by 2
“The main issue is the lack of public datasets, which we resolved by creating the first fisheye camera dataset called WoodScape [12] and baseline object detection models [13] in our previous work.”
Self-citationAbdi, B., Rokhi, Z., Vidal, C., et al. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3589203 · Cited by 2
Synthetic Dataset Generation Using Logical Scenario Files for Automotive Perception Testing
García, M., Iglesias, A., Sánchez, M., Naranjo, R., de Gordoa, J. A. Í., Nieto, M., & Aginako, N. (2025) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv64158.2025.11097801 · Cited by 3
“These are the main reasons why usually ADS validation is combined with virtual testing using high-fidelity simulation engines, as can be seen in the multiple synthetic datasets replicating real vehicle sensor setups [8]–[11].”
3-D Object Detection for Railway: A Comprehensive Survey
Lian, L., Qin, Y., Cao, Z., Gao, Y., Liu, Z., Li, Q., & Cheng, X. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3684649 · Cited by 2
DSA: Deformable Segmentation Attention for Multi-Scale Fisheye Image Segmentation
Jiang, J., Xu, C., Liu, H., Fu, Y., & Jian, M. (2023) · Electronics · doi:10.3390/electronics12194059 · Cited by 2
Environmental Perception Using Fish-Eye Cameras for Autonomous Driving
Qian, Y., Yang, M. Z., & Dolan, J. M. (2023) · Advances in computer vision and pattern recognition · doi:10.1007/978-981-99-4287-9_2 · Cited by 3
Object Detection via Fisheye Camera
Hsieh, Y., Chen, H.-C., & Yeh, Y.-H. (2023) · ACM Multimedia Asia (MMAsia) · doi:10.1145/3595916.3628351 · Cited by 2
“The name WoodScape [16] pays tribute to Robert Wood, the inventor of the fisheye camera in 1906.”
BackgroundModel-Free Rectification via Cascaded Distortion Model and Enhanced Backward Flow Network
Zhao, J., Wei, S., Chang, Y., et al. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3359663 · Cited by 2
“Initially, we select a set of 100 fisheye images from the real-world fisheye dataset Wood-scape [41] to serve as test samples.”
BackgroundMethodRevisiting Calibration of Wide-Angle Radially Symmetric Cameras
Cin, A. P. D., Azzoni, F., Boracchi, G., & Magri, L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72764-1_13 · Cited by 2
Occlusion-Aware Seamless Segmentation
Cao, Y., Zhang, J., Shi, H., et al. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72655-2_8 · Cited by 2
Zhou, J., Lin, C., Yang, S., et al. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3555836 · Cited by 2
“While creating the dataset, we noticed that existing road-way datasets [27], [28] are available publicly, which were collected using vehicle-mounted fisheye cameras.”
Vision-Based Sensing Systems for Autonomous Driving: Centralized or Decentralized?
Hirabayashi, M., Saito, Y., Murakami, K., et al. (2021) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2021.p0686 · Cited by 2
Improved Face Detector on Fisheye Images via Spherical-Domain Attention
Miao, J., Liu, Y., Liu, J., Argyriou, A., Xu, Z., & Han, Y. (2021) · IEEE Symposium on Computers and Communications (ISCC) · doi:10.1109/iscc53001.2021.9631545 · Cited by 2
“For autonomous driving [1], intelligent 360-degree monitoring [2] is essential for rapidly detecting and recognizing the target in the omni-view scene.”
BackgroundElamir, M. S., Gotzig, H., Zöllner, R., et al. (2022) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2234/1/012009 · Cited by 2
“In recent publications as well, we see work by researchers in Valeo [2] where a network of fish-eye cameras is used to provide a large dataset for training neural network-based systems for semantic segmentation of the vehicle surroundings into predefined classes.”
MethodDUET: Joint Deployment of Trucks and Drones for Object Monitoring
Wang, L., Wang, W., Dai, H., et al. (2022) · IEEE/ACM International Symposium on Quality of Service (IWQoS) · doi:10.1109/iwqos54832.2022.9812917 · Cited by 2
“(1) The QoM affects the application of obtained images heavily [6]– [8].”
Background
Metadata
- Authors
- Yogamani, S., Hughes, C., Horgan, J., Sistu, G., Chennupati, S., Uricar, M., Milz, S., Simon, M., Amende, K., Witt, C., Rashed, H., Nayak, S., Mansoor, S., Varley, P., Perrotton, X., Odea, D., & Perez, P.
- Affiliations
- Valeo (France) (FR)
- Venue
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2019-10
- Pages
- 9307-9317
- OpenAlex
- W2943449463
- Semantic Scholar
- 57de1a6cc6035d4ac6305121367ad3c6d3fd5104
- Cited by
- 334
- References
- 78
- Citations by year
- 2026: 32 · 2025: 55 · 2024: 61 · 2023: 74 · 2022: 47 · 2021: 40 · 2020: 16 · 2019: 9
- FWCI
- 9.05
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Keywords
- fisheye camera, surround-view cameras, autonomous driving, semantic segmentation, depth estimation, soiling detection
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
