mlsanityData to 7 Oct 2026

What Matters in Unsupervised Optical Flow

arXiv 2006.04902 ↗First posted 8 Jun 2020cs.CV cs.LG eess.IVcited by 124

Not on the map. Why?

Abstract (arXiv)

We systematically compare and analyze a set of key components in unsupervised optical flow to identify which photometric loss, occlusion handling, and smoothness regularization is most effective. Alongside this investigation we construct a number of novel improvements to unsupervised flow models, such as cost volume normalization, stopping the gradient at the occlusion mask, encouraging smoothness before upsampling the flow field, and continual self-supervision with image resizing. By combining the results of our investigation with our improved model components, we are able to present a new unsupervised flow technique that significantly outperforms the previous unsupervised state-of-the-art and performs on par with supervised FlowNet2 on the KITTI 2015 dataset, while also being significantly simpler than related approaches.

Key facts. Cited by 124 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 23; 2022: 31; 2023: 30; 2024: 18; 2025: 14; 2026: 8.

124 papers.

Sort:

By area:

  1. 2021PIRenderer: Controllable Portrait Image Generation via Semantic Neural Renderingcited by 202
  2. 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
  3. 2021XVFI: eXtreme Video Frame Interpolationcited by 123
  4. 2021AutoFlow: Learning a Better Training Set for Optical Flowcited by 102
  5. 2021Asymmetric Bilateral Motion Estimation for Video Frame Interpolationcited by 101
  6. 2021SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warpingcited by 74
  7. 2021CCVS: Context-aware Controllable Video Synthesiscited by 68
  8. 2022Multi-Frame Self-Supervised Depth with Transformerscited by 64
  9. 2024COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editingcited by 59
  10. 2023A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyondcited by 55
  11. 2023A Dynamic Multi-Scale Voxel Flow Network for Video Predictioncited by 53
  12. 2023MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Featurescited by 53
38 more
  1. 2022Dense Continuous-Time Optical Flow from Events and Framescited by 45
  2. 2022Learning Pixel Trajectories with Multiscale Contrastive Random Walkscited by 36
  3. 2023Tracking and Mapping in Medical Computer Vision: A Reviewcited by 36
  4. 2021Neural Video Compression using GANs for Detail Synthesis and Propagationcited by 35
  5. 2022Disentangling Architecture and Training for Optical Flowcited by 32
  6. 2022Learning Optical Flow, Depth, and Scene Flow without Real-World Labelscited by 31
  7. 2022What Matters for 3D Scene Flow Networkcited by 31
  8. 2021Self-Supervised Multi-Frame Monocular Scene Flowcited by 29
  9. 2021Learning optical flow from still imagescited by 28
  10. 2022DiffPoseNet: Direct Differentiable Camera Pose Estimationcited by 27
  11. 2022Imposing Consistency for Optical Flow Estimationcited by 24
  12. 2024Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimationcited by 24
  13. 2025Event-Based Video Frame Interpolation With Cross-Modal Asymmetric Bidirectional Motion Fieldscited by 24
  14. 2023BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolationcited by 23
  15. 2024Let Occ Flow: Self-Supervised 3D Occupancy Flow Predictioncited by 23
  16. 2022RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videoscited by 22
  17. 2022Visuomotor Control in Multi-Object Scenes Using Object-Aware Representationscited by 21
  18. 2022Dressing in the Wild by Watching Dance Videoscited by 20
  19. 2022Sound Localization by Self-Supervised Time Delay Estimationcited by 18
  20. 2021Comparing Correspondences: Video Prediction with Correspondence-wise Lossescited by 16
  21. 2021Occlusion-aware Unsupervised Learning of Depth from 4-D Light Fieldscited by 16
  22. 2021GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learningcited by 15
  23. 2022Context-Aware Video Reconstruction for Rolling Shutter Camerascited by 15
  24. 2022Optical Flow Training under Limited Label Budget via Active Learningcited by 14
  25. 2023DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labelingcited by 14
  26. 2023SENDD: Sparse Efficient Neural Depth and Deformation for Tissue Trackingcited by 14
  27. 2022Spatial-then-Temporal Self-Supervised Learning for Video Correspondencecited by 13
  28. 2024BiM-VFI: Bidirectional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motionscited by 13
  29. 2024Refining Pre-Trained Motion Modelscited by 12
  30. 2024PooDLe: Pooled and dense self-supervised learning from naturalistic videoscited by 11
  31. 2022MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillationcited by 10
  32. 2022Self-supervised AutoFlowcited by 10
  33. 2023GyroFlow+: Gyroscope-Guided Unsupervised Deep Homography and Optical Flow Learningcited by 10
  34. 2023Self-Supervised Motion Magnification by Backpropagating Through Optical Flowcited by 10
  35. 2024Self-Supervised Any-Point Tracking by Contrastive Random Walkscited by 10
  36. 2025Scene-Centric Unsupervised Panoptic Segmentationcited by 10
  37. 2025FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Basescited by 10
  38. 2022Semi-Supervised Learning of Optical Flow by Flow Supervisorcited by 9

50 most cited of 124 All 124 (JSON)