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
30 Own result · 30 No basis given · 11 Couldn’t confirm · 10 No full text of the sources · 4 Own interpretation · 3 Own method · 1 Partly supported · 1 Not supported · 1 Sources not found · 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.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The 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)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- 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)
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- 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)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- 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)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a 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
“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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says 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
“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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a 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
“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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- 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.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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)
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“We introduce WoodScape, the first fisheye image dataset dedicated to autonomous driving.”
§ WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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:
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“| 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“| 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It 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:
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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:
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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”
BackgroundnuScenes: A Multimodal Dataset for Autonomous Driving
Caesar, H., Bankiti, V., Lang, A. H., Vora, S., Liong, V. E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., & Beijbom, O. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01164 · Cited by 7,152 · cited 1×
“Task/Info Quantity KITTI [17] Cityscapes [10] Mapillary [39] nuScenes [6] ApolloScape [24] BDD100k [59] WoodScape Ours”
BackgroundLSD-SLAM: Large-scale direct monocular SLAM
Engel, J., Schöps, T., & Cremers, D. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10605-2_54 · Cited by 3,851 · cited 8×
“Some examples of the few datasets that have fisheye are: Visual SLAM ground truth for indoor scenes with omnidirectional cameras in [7], SphereNet [9] containing 1200 labelled images of parked cars using 360° cameras (not strictly fisheye) and, in automotive, the Oxford Robotcar 1 ar X iv :1 90 5.”
BackgroundMethodInfluentialCARLA: An open urban driving simulator
Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., & Koltun, V. (2017) · arXiv · doi:10.48550/arxiv.1711.03938 · Cited by 3,718
End to End Learning for Self-Driving Cars
Bojarski, M., Del Testa, D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., Jackel, L. D., Monfort, M., Muller, U., Zhang, J., et al. (2016) · arXiv · doi:10.48550/arxiv.1604.07316 · Cited by 3,198 · cited 1×
“demonstrated end-to-end learning [2] for steering and recently it was applied to fisheye cameras [54].”
BackgroundEigen, D., & Fergus, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.304 · Cited by 2,862 · cited 2×
“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.”
MethodInfluentialRos, G., Sellart, L., Materzynska, J., Vazquez, D., & Lopez, A. M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.352 · Cited by 2,338 · cited 1×
“There are several popular synthetic datasets like SYNTHIA [44] and CARLA [13].”
MethodENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
Paszke, A., Chaurasia, A., Kim, S., & Culurciello, E. (2016) · arXiv · doi:10.48550/arxiv.1606.02147 · Cited by 1,826 · cited 2×
“We use ENet [41] to generate our baseline results.”
Method1 year, 1000 km: The Oxford RobotCar dataset
Maddern, W., Pascoe, G., Linegar, C., & Newman, P. (2017) · The International Journal of Robotics Research · doi:10.1177/0278364916679498 · Cited by 1,632
The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes
Neuhold, G., Ollmann, T., Bulo, S. R., & Kontschieder, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.534 · Cited by 1,434 · cited 2×
“Task/Info Quantity KITTI [17] Cityscapes [10] Mapillary [39] nuScenes [6] ApolloScape [24] BDD100k [59] WoodScape Ours”
BackgroundMultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving
Teichmann, M., Weber, M., Zollner, M., Cipolla, R., & Urtasun, R. (2018) · 2018 IEEE Intelligent Vehicles Symposium (IV) · doi:10.1109/ivs.2018.8500504 · Cited by 681 · cited 1×
“However, there is a recent trend [30, 53, 51, 8] to solve tasks using a single multi-task model to enable efficient reuse of encoder features and also”
BackgroundThe ApolloScape Dataset for Autonomous Driving
Huang, X., Cheng, X., Geng, Q., Cao, B., Zhou, D., Wang, P., Lin, Y., & Yang, R. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00141 · Cited by 679 · cited 2×
“Task/Info Quantity KITTI [17] Cityscapes [10] Mapillary [39] nuScenes [6] ApolloScape [24] BDD100k [59] WoodScape Ours”
Background(2018) · arXiv (Cornell University) · Cited by 679
Kokkinos, I. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.579 · Cited by 657 · cited 1×
“However, there is a recent trend [30, 53, 51, 8] to solve tasks using a single multi-task model to enable efficient reuse of encoder features and also”
BackgroundDeepFakes: a New Threat to Face Recognition? Assessment and Detection
Korshunov, P., & Marcel, S. (2018) · arXiv · doi:10.48550/arxiv.1812.08685 · Cited by 497 · cited 1×
“is also the possibility of using GAN based re-targeting wherein faces are exchanged by automatically generated ones [31].”
BackgroundOn the Class Imbalance Problem
Guo, X., Yin, Y., Dong, C., Yang, G., & Zhou, G. (2008) · 2008 Fourth International Conference on Natural Computation · doi:10.1109/icnc.2008.871 · Cited by 495 · cited 1×
“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.”
BackgroundCoors, B., Condurache, A., & Geiger, A. (2018) · European Conference on Computer Vision · doi:10.1007/978-3-030-01240-3_32 · Cited by 457 · cited 3×
“Some examples of the few datasets that have fisheye are: Visual SLAM ground truth for indoor scenes with omnidirectional cameras in [7], SphereNet [9] containing 1200 labelled images of parked cars using 360° cameras (not strictly fisheye) and, in automotive, the Oxford Robotcar”
MethodDeep Learning is Robust to Massive Label Noise
Rolnick, D., Veit, A., Belongie, S., & Shavit, N. (2017) · arXiv · doi:10.48550/arxiv.1705.10694 · Cited by 402 · cited 1×
“unately, due to the overwhelming success of deep learning, recently it does not get as much attention as it still deserves in our opinion. Deep learning was shown to be quite resistant to label noise [41]. However, at the same time, it was shown that careful inspection of the training sets for outliers improves the ro…”
BackgroundAugmented reality: Principles and practice
Schmalstieg, D., & Hollerer, T. (2017) · 2017 IEEE Virtual Reality (VR) · doi:10.1109/vr.2017.7892358 · Cited by 397
A review of instance selection methods
Olvera-López, J. A., Carrasco-Ochoa, J. A., Martínez-Trinidad, J. F., & Kittler, J. (2010) · Artificial Intelligence Review · doi:10.1007/s10462-010-9165-y · Cited by 395 · cited 2×
“We used a combination of a wrapper method using selection criterion based on the classifier’s accuracy [40] and a simple filter based on the image similarity measurement.”
MethodComplex-YOLO: An Euler-Region-Proposal for Real-Time 3D Object Detection on Point Clouds
Simón, M., Milz, S., Amende, K., & Groß, H. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11009-3_11 · Cited by 367 · cited 2×
“1°) 71 Visual SLAM LSD SLAM [15] Relocalization (%) 61 3D Bounding Box Detection - Complex YOLO [50] Metric for Training AP (%) AOS (%) Runtime (ms)”
BackgroundMethodSelf-citationEuroCity Persons: A Novel Benchmark for Person Detection in Traffic Scenes
Braun, M., Krebs, S., Flohr, F., & Gavrila, D. M. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2897684 · Cited by 307 · cited 1×
“In the recent EuroCity persons dataset [5], the authors argued that any anonymization measure will introduce a bias.”
BackgroundPless, R. (2003) · 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings. · doi:10.1109/cvpr.2003.1211520 · Cited by 291 · cited 1×
“Pless [42] did pioneering work in deriving a framework for modeling a network of cameras as one, this approach is useful for geometric vision algorithms like visual odometry.”
BackgroundLarge-scale direct SLAM for omnidirectional cameras
Caruso, D., Engel, J., & Cremers, D. (2015) · 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353366 · Cited by 244 · cited 4×
“As a comparison, to give the reader an understanding of how different models behave, Figure 3 shows the mapping function r(θ) for five different projection models, which are Polynomial, Rectilinear, Stereographic, UCM and eUCM.”
MethodInfluentialBDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
Yu, F., Chen, H., Wang, X., Xian, W., Chen, Y., Liu, F., Madhavan, V., & Darrell, T. (2018) · arXiv · doi:10.48550/arxiv.1805.04687 · Cited by 204
On Issues of Instance Selection
Liu, H., & Motoda, H. (2002) · Data Mining and Knowledge Discovery · doi:10.1023/a:1014056429969 · Cited by 191 · cited 1×
“One frequently used approach is instance selection [40, 35, 26].”
MethodDeep semantic segmentation for automated driving: Taxonomy, roadmap and challenges
Siam, M., Elkerdawy, S., Jagersand, M., & Yogamani, S. (2017) · 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2017.8317714 · Cited by 178 · cited 1×
“Semantic segmentation networks for autonomous driving [47] have been successfully trained directly on fisheye images in [12, 45].”
Self-citationMultiNet: Real-time Joint Semantic Reasoning for Autonomous DrivingPreprint
Teichmann, M., Weber, M., Zöllner, M., Cipolla, R., & Urtasun, R. (2016) · arXiv (Cornell University) · doi:10.17863/cam.26778 · Cited by 177
Weakly- and Semi-supervised Panoptic Segmentation
Li, Q., Arnab, A., & Torr, P. H. S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01267-0_7 · Cited by 171 · cited 1×
“The dataset also provides instance segmentation labels to explore panoptic segmentation models [34].”
MethodKernel Transformer Networks for Compact Spherical Convolution
Su, Y.-C., & Grauman, K. L. (2019) · 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/cvpr.2019.00967 · Cited by 136 · cited 1×
“This had led to several adaptations of CNN to handle spherical images such as [52] and [9].”
MethodAccuracy of fish-eye lens models
Eising, C., Denny, P. E., Jones, E., & Glavin, M. (2010) · Applied Optics · doi:10.1364/ao.49.003338 · Cited by 133 · cited 1×
“More detailed analysis of accuracy of various projection models is discussed in [25].”
BackgroundSelf-citationComparison of Instances Seletion Algorithms I. Algorithms Survey
Jankowski, N., & Grochowski, M. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-24844-6_90 · Cited by 132
Computer vision in automated parking systems: Design, implementation and challenges
Heimberger, M., Horgan, J., Hughes, C., McDonald, J., & Yogamani, S. (2017) · Image and Vision Computing · doi:10.1016/j.imavis.2017.07.002 · Cited by 126 · cited 1×
“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.”
BackgroundSelf-citationRTSeg: Real-Time Semantic Segmentation Comparative Study
Siam, M., Gamal, M., Abdel-Razek, M., Yogamani, S., & Jagersand, M. (2018) · 2018 25th IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2018.8451495 · Cited by 112 · cited 1×
“This has been explored in [49, 57, 48] for narrow angle cameras.”
BackgroundSelf-citationCNN based semantic segmentation for urban traffic scenes using fisheye camera
Deng, L., Yang, M., Qian, Y., Wang, C., & Wang, B. (2017) · 2017 IEEE Intelligent Vehicles Symposium (IV) · doi:10.1109/ivs.2017.7995725 · Cited by 111 · cited 1×
“Semantic segmentation networks for autonomous driving [47] have been successfully trained directly on fisheye images in [12, 45].”
Visual SLAM for Automated Driving: Exploring the Applications of Deep Learning
Milz, S., Arbeiter, G., Witt, C., Abdallah, B., & Yogamani, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00062 · Cited by 107 · cited 1×
“Visual Odometry (VO) is necessary for creating a map from the objects detected [38].”
BackgroundSelf-citationMODNet: Motion and Appearance based Moving Object Detection Network for Autonomous Driving
Siam, M., Mahgoub, H., Zahran, M., Yogamani, S., Jagersand, M., & El-Sallab, A. (2018) · 2018 21st International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2018.8569744 · Cited by 95 · cited 4×
“Using MODNet as baseline network, we achieve an IoU of 45.”
BackgroundMethodInfluentialSelf-citationSelecting Representative Data Sets
Borovicka, T., Jirina, M., Kordik, P., & Jiri, M. (2012) · Advances in Data Mining Knowledge Discovery and Applications · doi:10.5772/50787 · Cited by 94 · cited 1×
“ing conventions, which we will refer to first (we follow the definitions provided in [4]).”
BackgroundVision-Based Driver Assistance Systems: Survey, Taxonomy and Advances
Horgan, J., Hughes, C., McDonald, J., & Yogamani, S. (2015) · 2015 IEEE 18th International Conference on Intelligent Transportation Systems · doi:10.1109/itsc.2015.329 · Cited by 72 · cited 1×
“Large FOV cameras are necessary for various computer vision application domains, including video surveillance [28] and augmented reality [46], and have been of particular interest in autonomous driving [23].”
BackgroundSelf-citationSMSnet: Semantic motion segmentation using deep convolutional neural networks
Vertens, J., Valada, A., & Burgard, W. (2017) · 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8202211 · Cited by 69 · cited 1×
“This has been explored in [49, 57, 48] for narrow angle cameras.”
BackgroundArea projections of fisheye photographic lenses
Herbert, T. J. (1987) · Agricultural and Forest Meteorology · doi:10.1016/0168-1923(87)90039-6 · Cited by 67 · cited 1×
“Stereographic projection [22] is the simplest model which uses a mapping from a sphere to a plane.”
BackgroundAn Enhanced Unified Camera Model
Khomutenko, B., Garcia, G., & Martinet, P. (2016) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2015.2502921 · Cited by 58 · cited 3×
“As a comparison, to give the reader an understanding of how different models behave, Figure 3 shows the mapping function r(θ) for five different projection models, which are Polynomial, Rectilinear, Stereographic, UCM and eUCM.”
MethodYes, we GAN: Applying adversarial techniques for autonomous driving
Uřičář, M., Křížek, P., Hurych, D., Sobh, I., Yogamani, S. K., & Denny, P. E. (2019) · Electronic Imaging · doi:10.2352/issn.2470-1173.2019.15.avm-048 · Cited by 58 · cited 1×
“The task of soiling detection was to our best knowledge first defined in [56].”
BackgroundSelf-citationFisheye lens camera based surveillance system for wide field of view monitoring
Kim, H., Jung, J., & Paik, J. (2016) · Optik · doi:10.1016/j.ijleo.2016.03.069 · Cited by 53 · cited 1×
“Large FOV cameras are necessary for various computer vision application domains, including video surveillance [28] and augmented reality [46], and have been of particular interest in autonomous driving [23].”
BackgroundKúkelová, Z., Heller, J., Bujnak, M., & Pajdla, T. (2015) · 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/cvpr.2015.7298663 · Cited by 49 · cited 1×
“[32] extend homography estimation by incorporating radial distortion model.”
MethodAuxNet: Auxiliary Tasks Enhanced Semantic Segmentation for Automated Driving
Chennupati, S., Sistu, G., Yogamani, S., & Rawashdeh, S. (2019) · Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications · doi:10.5220/0007684106450652 · Cited by 42 · cited 1×
“However, there is a recent trend [30, 53, 51, 8] to solve tasks using a single multi-task model to enable efficient reuse of encoder features and also”
BackgroundSelf-citationCNN-based Fisheye Image Real-Time Semantic Segmentation
Saez, A., Bergasa, L. M., Romeral, E., López-Guillén, E., Barea, R., & Sanz, R. (2018) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2018.8500456 · Cited by 40 · cited 1×
“Semantic segmentation networks for autonomous driving [47] have been successfully trained directly on fisheye images in [12, 45].”
End to End Vehicle Lateral Control Using a Single Fisheye Camera
Toromanoff, M., Wirbel, É., Wilhelm, F., Vejarano, C., Perrotton, X., & Moutarde, F. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594090 · Cited by 36 · cited 1×
“demonstrated end-to-end learning [2] for steering and recently it was applied to fisheye cameras [54].”
BackgroundSelf-citationNeurAll: Towards a Unified Visual Perception Model for Automated Driving
Sistu, G., Leang, I., Chennupati, S., Yogamani, S. K., Eising, C., Milz, S., & Rawashdeh, S. A. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8917043 · Cited by 36
Self-citationXXIII. Fish-eye views, and vision under water
Wood, R. W. (1906) · The London Edinburgh and Dublin Philosophical Magazine and Journal of Science · doi:10.1080/14786440609463529 · Cited by 30 · cited 1×
“Robert Wood originally coined the term in 1906 [58], and constructed a basic fisheye camera by taking a pin-hole camera and filling it with water.”
BackgroundUnifying Image Plane Liftings for Central Catadioptric and Dioptric Cameras
Barreto, J. P. (2006) · Imaging Beyond the Pinhole Camera · doi:10.1007/978-1-4020-4894-4_2 · Cited by 26 · cited 3×
“As a comparison, to give the reader an understanding of how different models behave, Figure 3 shows the mapping function r(θ) for five different projection models, which are Polynomial, Rectilinear, Stereographic, UCM and eUCM.”
MethodLXXXIX. A wide angle lens for cloud recording
Bond, W. N. (1922) · The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science · doi:10.1080/14786441208562576 · Cited by 26 · cited 1×
“It was later replaced with a hemispherical lens [3].”
BackgroundChallenges in Designing Datasets and Validation for Autonomous Driving
Uřičář, M., Hurych, D., Křížek, P., & Yogamani, S. K. (2019) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0007690700002108 · Cited by 17
Self-citationChallenges in Designing Datasets and Validation for Autonomous Driving
Uřičář, M., Hurych, D., Křížek, P., & Yogamani, S. K. (2019) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0007690706530659 · Cited by 14 · cited 1×
“The dataset supports correct hypothesis evaluation [55], therefore multiple splits are provided (5 in total).”
BackgroundSelf-citationLess is More: Culling the Training Set to Improve Robustness of Deep Neural Networks
Liu, Y.-S., Chen, J.-Y., & Chen, H. (2018) · Decision and Game Theory for Security · doi:10.48550/arxiv.1801.02850 · Cited by 14
Less is More: Culling the Training Set to Improve Robustness of Deep Neural Networks
Liu, Y., Chen, J., & Chen, H. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01554-1_6 · Cited by 12 · cited 1×
“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.”
BackgroundNeurAll: Towards a Unified Model for Visual Perception in Automated DrivingPreprint
Sistu, G., Leang, I., Chennupati, S., Hughes, C., Milz, S., Yogamani, S. K., & Rawashdeh, S. A. (2019) · arXiv (Cornell University) · Cited by 11
Self-citationNeurAll: Towards a Unified Visual Perception Model for Automated DrivingPreprint
Sistu, G., Leang, I., Chennupati, S., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.03589
Self-citationAugmented Reality – Principles and Practice Tutorial
Schmalstieg, D., & Höllerer, T. (2016) · 2016 IEEE International Symposium on Mixed and Augmented Reality (ISMAR-Adjunct) · doi:10.1109/ismar-adjunct.2016.0015
Fisheye lens-based surveillance camera for wide field-of-view monitoring
Kim, H., Chae, E., Jo, G., et al. (2015) · 2015 IEEE International Conference on Consumer Electronics (ICCE) · doi:10.1109/icce.2015.7066501
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
Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo, W.-Y., et al. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00371 · Cited by 11,953
“-20 0 +20 +40 IoU delta at 1 center point GTEA [34, 63] TrashCan [52] DRAM [24] PIDRay [104] Cityscapes [25] WoodScape [112] IBD [17] EgoHOS [113] Plittersdorf [46] VISOR [28, 27] NDISPark [22, 23] Hypersim [86] OVIS [81] ADE20K [117] iShape [111] ZeroWaste-f [6] STREETS [91] LVIS [44] NDD20 [100] TimberSeg [38] DOORS…”
BackgroundMethodInfluentialnuScenes: A Multimodal Dataset for Autonomous Driving
Caesar, H., Bankiti, V., Lang, A. H., Vora, S., Liong, V. E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., & Beijbom, O. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01164 · Cited by 7,152
“Similar to [84], nuScenes is a holistic scene understanding benchmark for AVs.”
BackgroundDeep reinforcement learning for autonomous driving: A survey
Kiran, B. R., Sobh, I., Talpaert, V., Mannion, P., Sallab, A. A. A., Yogamani, S., & Perez, P. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3054625 · Cited by 2,342
“into a multi-task model [8], [9].”
Self-citationSensor and Sensor Fusion Technology in Autonomous Vehicles: A Review
Yeong, D. J., Velasco-Hernandez, G., Barry, J., & Walsh, J. L. (2021) · Sensors · doi:10.3390/s21062140 · Cited by 1,187
“Other commonly employed cameras in AVs for perception of the surroundings include fisheye cameras [46-48].”
BackgroundKITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D
Liao, Y., Xie, J., & Geiger, A. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3179507 · Cited by 770
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
