The DOI matches its Crossref record; 55 of the 55 references it cites were found in a registry or an index.
Self-Supervised Learning With Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Camera
Open accessAbstract
We present GLNet, a self-supervised framework for learning depth, optical flow, camera pose and intrinsic parameters from monocular video - addressing the difficulty of acquiring realistic ground-truth for such tasks. We propose three contributions: 1) we design new loss functions that capture multiple geometric constraints (eg. epipolar geometry) as well as adaptive photometric loss that supports multiple moving objects, rigid and non-rigid, 2) we extend the model such that it predicts camera intrinsics, making it applicable to uncalibrated video, and 3) we propose several online refinement strategies that rely on the symmetry of our self-supervised loss in training and testing, in particular optimizing model parameters and/or the output of different tasks, leveraging their mutual interactions. The idea of jointly optimizing the system output, under all geometric and photometric constraints can be viewed as a dense generalization of classical bundle adjustment. We demonstrate the effectiveness of our method on KITTI and Cityscapes, where we outperform previous self-supervised approaches on multiple tasks. We also show good generalization for transfer learning.
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
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892
Multiple View Geometry in Computer Vision
Hartley, R., & Zisserman, A. (2004) · doi:10.1017/cbo9780511811685 · Cited by 21,070
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472
SURF: Speeded Up Robust Features
Bay, H., Tuytelaars, T., & Van Gool, L. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_32 · Cited by 14,955
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
The 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
Vision 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
Structure-from-Motion Revisited
Schonberger, J. L., & Frahm, J.-M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.445 · Cited by 6,433
Flownet: Learning optical flow with convolutional networks
Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., Smagt, P. V. D., Cremers, D., & Brox, T. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.316 · Cited by 4,313
Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
Eigen, D., Puhrsch, C., & Fergus, R. (2014) · arXiv · doi:10.48550/arxiv.1406.2283 · Cited by 3,442
Unsupervised Monocular Depth Estimation with Left-Right Consistency
Godard, C., Aodha, O. M., & Brostow, G. J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.699 · Cited by 3,270 · cited 2×
“equipment like laser or stereo rigs with sensitive calibration [10]. Another option is to use synthetic data [28], however bridging the realism gap can be challenging. More recently, several authors [12,48] focused on designing self-supervised systems with training signals resulting from photometric consistency losses…”
BackgroundMethodFlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., & Brox, T. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.179 · Cited by 3,152
Multiple view geometry in computer vision
Opower, H. (2002) · Optics and Lasers in Engineering · doi:10.1016/s0143-8166(01)00145-2 · Cited by 3,007
Unsupervised Learning of Depth and Ego-Motion from Video
Zhou, T., Brown, M., Snavely, N., & Lowe, D. G. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.700 · Cited by 2,910
Eigen, D., & Fergus, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.304 · Cited by 2,862
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
Digging Into Self-Supervised Monocular Depth Estimation
Godard, C., Aodha, O. M., Firman, M., & Brostow, G. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00393 · Cited by 2,561
PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization
Kendall, A., Grimes, M., & Cipolla, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.336 · Cited by 2,489
Mayer, 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
DTAM: 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×
“Structure from motion (SfM) [11, 17, 34, 37, 39, 44] or scene flow estimation [33, 40] are well-established methodologies with a solid record of fundamental and practical progress.”
BackgroundDeeper Depth Prediction with Fully Convolutional Residual Networks
Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., & Navab, N. (2016) · 2016 Fourth International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2016.32 · Cited by 1,982
Domain Adaptive Faster R-CNN for Object Detection in the Wild
Chen, Y., Li, W., Sakaridis, C., Dai, D., & Van Gool, L. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00352 · Cited by 1,672
Self-citationUnsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
Garg, R., B.G., V. K., Carneiro, G., & Reid, I. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46484-8_45 · Cited by 1,632
Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
Garg, R., BG, V. K., Carneiro, G., & Reid, I. (2016) · arXiv · doi:10.48550/arxiv.1603.04992 · Cited by 1,632
Optical Flow Estimation Using a Spatial Pyramid Network
Ranjan, A., & Black, M. J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.291 · Cited by 1,344
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
Mayer, N., Ilg, E., Cremers, D., Dosovitskiy, A., & Brox, T. (2016) · Cited by 1,214
Taskonomy: Disentangling Task Transfer Learning
Zamir, A. R., Sax, A., Shen, W., Guibas, L., Malik, J., & Savarese, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00391 · Cited by 1,128
Geometric Loss Functions for Camera Pose Regression with Deep Learning
Kendall, A., & Cipolla, R. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.694 · Cited by 803
Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints
Mahjourian, R., Wicke, M., & Angelova, A. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00594 · Cited by 775
Towards Internet-scale multi-view stereo
Furukawa, Y., Curless, B., Seitz, S. M., & Szeliski, R. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539802 · Cited by 751
Zhan, H., Garg, R., Weerasekera, C. S., Li, K., Agarwal, H., & Reid, I. M. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00043 · Cited by 705
VisualSFM:A visual structure from motion system,
Wu, C. (2011) · Medical Entomology and Zoology · Cited by 698
Learning Depth from Monocular Videos Using Direct Methods
Wang, C., Buenaposada, J. M., Zhu, R., & Lucey, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00216 · Cited by 667
Ranjan, A., Jampani, V., Balles, L., Kim, K., Sun, D., Wulff, J., & Black, M. J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01252 · Cited by 632
Li, B., Shen, C., Dai, Y., van den Hengel, A., & He, M. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298715 · Cited by 590
Modelling uncertainty in deep learning for camera relocalization
Kendall, A., & Cipolla, R. (2016) · 2016 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2016.7487679 · Cited by 548 · cited 1×
“Several methods train networks based on ground-truth labels and have been successfully applied to many tasks, such as monocular depth prediction [9, 10, 27, 28], optical flow [8, 19, 35, 38] and camera pose estimation [22, 23, 24].”
MethodUnFlow: Unsupervised Learning of Optical Flow With a Bidirectional Census Loss
Meister, S., Hur, J., & Roth, S. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12276 · Cited by 520
Xu, D., Ouyang, W., Wang, X., & Sebe, N. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00077 · Cited by 518
Casser, V., Pirk, S., Mahjourian, R., & Angelova, A. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018001 · Cited by 471
DF-Net: Unsupervised Joint Learning of Depth and Flow Using Cross-Task Consistency
Zou, Y., Luo, Z., & Huang, J.-B. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01228-1_3 · Cited by 469
Vedula, S., Baker, S., Rander, P., Collins, R., & Kanade, T. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790293 · Cited by 426
Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothness
Yu, J. J., Harley, A. W., & Derpanis, K. G. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-49409-8_1 · Cited by 368
SfM-Net: Learning of Structure and Motion from Video
Vijayanarasimhan, S., Ricco, S., Schmid, C., Sukthankar, R., & Fragkiadaki, K. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.07804 · Cited by 310
Self-citationROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes
Chen, Y., Li, W., & Gool, L. V. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00823 · Cited by 291
Self-citationAtapour-Abarghouei, A., & Breckon, T. P. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00296 · Cited by 276
Chen, Y., Li, W., Chen, X., & Van Gool, L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00194 · Cited by 230
Self-citationJoint Task-Recursive Learning for Semantic Segmentation and Depth Estimation
Zhang, Z., Cui, Z., Xu, C., Jie, Z., Li, X., & Yang, J. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01249-6_15 · Cited by 218
LEGO: Learning Edge with Geometry all at Once by Watching Videos
Yang, Z., Wang, P., Wang, Y., Xu, W., & Nevatia, R. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00031 · Cited by 192
Ilg, E., Saikia, T., Keuper, M., & Brox, T. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01258-8_38 · Cited by 185
Supervising the New with the Old: Learning SFM from SFM
Klodt, M., & Vedaldi, A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01249-6_43 · Cited by 175
Temporal Interpolation as an Unsupervised Pretraining Task for Optical Flow Estimation
Wulff, J., & Black, M. J. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-12939-2_39 · Cited by 13
Cited by
Self-supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance
Klingner, M., Termöhlen, J.-A., Mikolajczyk, J., & Fingscheidt, T. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58565-5_35 · Cited by 358
Consistent video depth estimation
Luo, X., Huang, J.-B., Szeliski, R., Matzen, K., & Kopf, J. (2020) · ACM Transactions on Graphics · doi:10.1145/3386569.3392377 · Cited by 322
Monocular depth estimation based on deep learning: An overview
Zhao, C., Sun, Q., Zhang, C., Tang, Y., & Qian, F. (2020) · Science China Technological Sciences · doi:10.1007/s11431-020-1582-8 · Cited by 310
A Comprehensive Survey on Test-Time Adaptation Under Distribution Shifts
Liang, J., He, R., & Tan, T. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-024-02181-w · Cited by 271
On the Uncertainty of Self-Supervised Monocular Depth Estimation
Poggi, M., Aleotti, F., Tosi, F., & Mattoccia, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00329 · Cited by 270
Metadata
- Authors
- Chen, Y., Schmid, C., & Sminchisescu, C.
- Venue
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2019-10
- Pages
- 7062-7071
- OpenAlex
- W2981732213
- Cited by
- 261
- References
- 55
- FWCI
- 12.65
- Type
- conference paper
- Language
- en
- Open access
- green
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.