Bounding Boxes, Segmentations and Object Coordinates: How Important is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios?
The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Existing methods for 3D scene flow estimation often fail in the presence of large displacement or local ambiguities, e.g., at texture-less or reflective surfaces. However, these challenges are omnipresent in dynamic road scenes, which is the focus of this work. Our main contribution is to overcome these 3D motion estimation problems by exploiting recognition. In particular, we investigate the importance of recognition granularity, from coarse 2D bounding box estimates over 2D instance segmentations to fine-grained 3D object part predictions. We compute these cues using CNNs trained on a newly annotated dataset of stereo images and integrate them into a CRF-based model for robust 3D scene flow estimation - an approach we term Instance Scene Flow. We analyze the importance of each recognition cue in an ablation study and observe that the instance segmentation cue is by far strongest, in our setting. We demonstrate the effectiveness of our method on the challenging KITTI 2015 scene flow benchmark where we achieve state-of-the-art performance at the time of submission.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
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 3×
“With the advent of challenging realworld benchmarks, such as the KITTI 2012 [10] and KITTI”
BackgroundMethodSelf-citationLSD-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 1×
“This observation is in accordance with recent works on direct visual odometry and SLAM [7, 8, 27] which use similar measures to reliably estimate the camera pose in weakly textured environments.”
ResultMayer, N., Ilg, E., Hausser, P., Fischer, P., Cremers, D., Dosovitskiy, A., & Brox, T. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.438 · Cited by 2,488
Object scene flow for autonomous vehicles
Menze, M., & Geiger, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298925 · Cited by 2,270 · cited 10×
“• High-quality, instance-level annotations of 400 stereo images from the KITTI 2015 benchmark [22].”
BackgroundMethodInfluentialSelf-citationDTAM: Dense tracking and mapping in real-time
Newcombe, R. A., Lovegrove, S. J., & Davison, A. J. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126513 · Cited by 2,078 · cited 1×
“This observation is in accordance with recent works on direct visual odometry and SLAM [7, 8, 27] which use similar measures to reliably estimate the camera pose in weakly textured environments.”
ResultInstance-aware Semantic Segmentation via Multi-task Network Cascades
Dai, J., He, K., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.04412 · Cited by 1,273
Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image
Brachmann, E., Michel, F., Krull, A., Yang, M. Y., Gumhold, S., & Rother, C. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.366 · Cited by 530 · cited 3×
“For fine-grained geometric recognition we train a new convolutional neural network (CNN) on 2D instance segmentations of MNC which predicts the continuous 3D object parts, also known as 3D object coordinates [3,4,25,33, 34], for each pixel inside the instance mask.”
BackgroundMethodSelf-citationMulti-view 3D Models from Single Images with a Convolutional Network
Tatarchenko, M., Dosovitskiy, A., & Brox, T. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46478-7_20 · Cited by 337 · cited 1×
“We use a modified version of the encoder-decoder style CNN proposed in [32] for estimating the object coordinates at each pixel.”
MethodExploiting uncertainty in regression forests for accurate camera relocalization
Valentin, J., Niebner, M., Shotton, J., Fitzgibbon, A., Izadi, S., & Torr, P. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299069 · Cited by 156 · cited 3×
“For fine-grained geometric recognition we train a new convolutional neural network (CNN) on 2D instance segmentations of MNC which predicts the continuous 3D object parts, also known as 3D object coordinates [3,4,25,33, 34], for each pixel inside the instance mask.”
BackgroundMethod
Cited by
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
Sun, D., Yang, X., Liu, M.-Y., & Kautz, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00931 · Cited by 2,648
GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
Yin, Z., & Shi, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00212 · Cited by 1,256
Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art
Janai, J., Güney, F., Behl, A., & Geiger, A. (2020) · Foundations and Trends® in Computer Graphics and Vision · doi:10.1561/0600000079 · Cited by 643
Self-citationM3D-RPN: Monocular 3D Region Proposal Network for Object Detection
Brazil, G., & Liu, X. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00938 · Cited by 591
SegStereo: Exploiting Semantic Information for Disparity Estimation
Yang, G., Zhao, H., Shi, J., Deng, Z., & Jia, J. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_39 · Cited by 375
Metadata
- Authors
- Behl, A., Jafari, O. H., Mustikovela, S. K., Alhaija, H. A., Rother, C., & Geiger, A.
- Venue
- 2017 IEEE International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2017-10
- Pages
- 2593-2602
- OpenAlex
- W2779333428
- Cited by
- 145
- References
- 9
- FWCI
- 5.99
- Type
- conference paper
- Language
- en
- Open access
- closed
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.
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.