The DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Abstract
The FlowNet demonstrated that optical flow estimation can be cast as a learning problem. However, the state of the art with regard to the quality of the flow has still been defined by traditional methods. Particularly on small displacements and real-world data, FlowNet cannot compete with variational methods. In this paper, we advance the concept of end-to-end learning of optical flow and make it work really well. The large improvements in quality and speed are caused by three major contributions: first, we focus on the training data and show that the schedule of presenting data during training is very important. Second, we develop a stacked architecture that includes warping of the second image with intermediate optical flow. Third, we elaborate on small displacements by introducing a subnetwork specializing on small motions. FlowNet 2.0 is only marginally slower than the original FlowNet but decreases the estimation error by more than 50%. It performs on par with state-of-the-art methods, while running at interactive frame rates. Moreover, we present faster variants that allow optical flow computation at up to 140fps with accuracy matching the original FlowNet.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
(1981) · Cited by 11,963
Two-Stream Convolutional Networks for Action Recognition in Videos
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1406.2199 · Cited by 6,756
Stacked Hourglass Networks for Human Pose Estimation
Newell, A., Yang, K., & Deng, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46484-8_29 · Cited by 5,634
Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 1×
“The strategy of training machine learning models on a series of gradually increasing tasks is known as curriculum learning [5].”
BackgroundUcf101: A dataset of 101 human actions classes from videos in the wild
Soomro, K., Zamir, A. R., & Shah, M. (2012) · arXiv · doi:10.48550/arxiv.1212.0402 · Cited by 4,575
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
Self-citationHigh Accuracy Optical Flow Estimation Based on a Theory for Warping
Brox, T., Bruhn, A., Papenberg, N., & Weickert, J. (2004) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-24673-2_3 · Cited by 2,570
Self-citationMayer, 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
Self-citationLearning and development in neural networks: the importance of starting small
Elman, J. L. (1993) · Cognition · doi:10.1016/0010-0277(93)90058-4 · Cited by 1,988 · cited 1×
“The idea dates back at least to Elman [11], who showed that both the evolution of tasks and the network architectures can be beneficial in the language processing scenario.”
BackgroundChen, Y., & Pock, T. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2596743 · Cited by 1,344
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
Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation
Brox, T., & Malik, J. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.143 · Cited by 1,295
Self-citationMayer, N., Ilg, E., Cremers, D., Dosovitskiy, A., & Brox, T. (2016) · Cited by 1,214
Self-citationDeepFlow: Large Displacement Optical Flow with Deep Matching
Weinzaepfel, P., Revaud, J., Harchaoui, Z., & Schmid, C. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.175 · Cited by 997
Human Pose Estimation with Iterative Error Feedback
Carreira, J., Agrawal, P., Fragkiadaki, K., & Malik, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.512 · Cited by 805
Object Segmentation by Long Term Analysis of Point Trajectories
Brox, T., & Malik, J. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15555-0_21 · Cited by 744
Self-citationEpicFlow: Edge-preserving interpolation of correspondences for optical flow
Revaud, J., Weinzaepfel, P., Harchaoui, Z., & Schmid, C. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298720 · Cited by 697
Segmentation of Moving Objects by Long Term Video Analysis
Ochs, P., Malik, J., & Brox, T. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.242 · Cited by 585
Self-citationDense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow
Sundaram, N., Brox, T., & Keutzer, K. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15549-9_32 · Cited by 422
Self-citationBack 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
Fast Optical Flow Using Dense Inverse Search
Kroeger, T., Timofte, R., Dai, D., & Van Gool, L. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_29 · Cited by 351
Recurrent Instance Segmentation
Romera-Paredes, B., & Torr, P. H. S. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46466-4_19 · Cited by 311
Bailer, C., Taetz, B., & Stricker, D. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.457 · Cited by 233
Motion Trajectory Segmentation via Minimum Cost Multicuts
Keuper, M., Andres, B., & Brox, T. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.374 · Cited by 199
Self-citationEfficient sparse-to-dense optical flow estimation using a learned basis and layers
Wulff, J., & Black, M. J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298607 · Cited by 181
Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow
Bao, L., Yang, Q., & Jin, H. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2359374 · Cited by 109
Unsupervised convolutional neural networks for motion estimation
Ahmadi, A., & Patras, I. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532634 · Cited by 103
Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow
Bao, L., Yang, Q., & Jin, H. (2014) · 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.2014.452 · Cited by 90
PatchBatch: A Batch Augmented Loss for Optical Flow
Gadot, D., & Wolf, L. (2016) · 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.2016.459 · Cited by 89
Güney, F., & Geiger, A. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-54190-7_13 · Cited by 54
Learning to Extract Motion from Videos in Convolutional Neural Networks
Teney, D., & Hebert, M. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-54193-8_26 · Cited by 52
Thewlis, J., Zheng, S., Torr, P. H. S., & Vedaldi, A. (2016) · British Machine Vision Conference (BMVC) · doi:10.5244/c.30.145 · Cited by 41
Learning to Extract Motion from Videos in Convolutional Neural NetworksPreprint
Teney, D., & Hebert, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1601.07532 · Cited by 31
Optical Flow Estimation using a Spatial Pyramid NetworkPreprint
Ranjan, A., & Black, M. J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.00850 · Cited by 20
CNN based Patch Matching for Optical Flow with Thresholded Hinge Loss.Preprint
Bailer, C., Varanasi, K., & Stricker, D. (2016) · arXiv (Cornell University) · Cited by 10
Research works printed but not linked: 2
- tran, 2016, Deep end2end voxe12voxel prediction (the 3rd workshop on deep learning in computer vision), IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- savva, 2015, Semantically-Enriched 3D Models for Common-sense Knowledge (Workshop on Functionality, Physics, Intentionality and Causality), IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Cited by
Deep High-Resolution Representation Learning for Human Pose Estimation
Sun, K., Xiao, B., Liu, D., & Wang, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00584 · Cited by 5,984
(2020) · doi:10.1007/978-3-030-58536-5_24 · Cited by 2,824
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
Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey
Jing, L., & Tian, Y. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2992393 · Cited by 2,036
Metadata
- Authors
- Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., & Brox, T.
- Venue
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2017-07
- Pages
- 1647-1655
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2560474170
- Cited by
- 3,152
- References
- 35
- FWCI
- 94.24
- 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.