mlsanityData to 7 Oct 2026

Self-supervised AutoFlow

arXiv 2212.01762 ↗First posted 4 Dec 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Recently, AutoFlow has shown promising results on learning a training set for optical flow, but requires ground truth labels in the target domain to compute its search metric. Observing a strong correlation between the ground truth search metric and self-supervised losses, we introduce self-supervised AutoFlow to handle real-world videos without ground truth labels. Using self-supervised loss as the search metric, our self-supervised AutoFlow performs on par with AutoFlow on Sintel and KITTI where ground truth is available, and performs better on the real-world DAVIS dataset. We further explore using self-supervised AutoFlow in the (semi-)supervised setting and obtain competitive results against the state of the art.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 41 of its 55 references that are in the map. First posted on arXiv 4 Dec 2022.

Builds on

41 of 55 references.

References · 41

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  4. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  5. 2021Vision Transformers for Dense Predictioncited by 1,789
  6. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  7. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  8. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  9. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 942
  10. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
  11. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 616
  12. 2016Optical Flow Estimation using a Spatial Pyramid Networkcited by 421
29 more
  1. 2022Kubric: A scalable dataset generatorcited by 373
  2. 2022FlowFormer: A Transformer Architecture for Optical Flowcited by 273
  3. 2021Learning to Estimate Hidden Motions with Global Motion Aggregationcited by 223
  4. 2022Particle Video Revisited: Tracking Through Occlusions Using Point Trajectoriescited by 215
  5. 2017UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Losscited by 202
  6. 2017Playing for Benchmarkscited by 169
  7. 2019SelFlow: Self-Supervised Learning of Optical Flowcited by 128
  8. 2020What Matters in Unsupervised Optical Flowcited by 124
  9. 2020Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimationcited by 120
  10. 2021LASR: Learning Articulated Shape Reconstruction from a Monocular Videocited by 115
  11. 2021AutoFlow: Learning a Better Training Set for Optical Flowcited by 102
  12. 2016Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothnesscited by 101
  13. 2017Occlusion Aware Unsupervised Learning of Optical Flowcited by 101
  14. 2018Creatures great and SMAL: Recovering the shape and motion of animals from videocited by 84
  15. 2022CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flowcited by 82
  16. 2021SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warpingcited by 74
  17. 2019DDFlow: Learning Optical Flow with Unlabeled Data Distillationcited by 63
  18. 2021High-Resolution Optical Flow from 1D Attention and Correlationcited by 54
  19. 2018What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?cited by 44
  20. 2022Disentangling Architecture and Training for Optical Flowcited by 32
  21. 2019Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenescited by 29
  22. 2021Learning optical flow from still imagescited by 28
  23. 2022RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videoscited by 22
  24. 2022Optical Flow Training under Limited Label Budget via Active Learningcited by 14
  25. 2016Unsupervised convolutional neural networks for motion estimationcited by 12
  26. 2018Conditional Prior Networks for Optical Flowcited by 11
  27. 2022Semi-Supervised Learning of Optical Flow by Flow Supervisorcited by 9
  28. 2022Multi-Scale RAFT: Combining Hierarchical Concepts for Learning-based Optical FLow Estimationcited by 9
  29. 2020Learnable Cost Volume Using the Cayley Representationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 3; 2026: 3.

10 papers.

  1. 2024BootsTAP: Bootstrapped Training for Tracking-Any-Pointcited by 115
  2. 2024UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Modelcited by 8
  3. 2025What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?cited by 7
  4. 2023Doduo: Learning Dense Visual Correspondence from Unsupervised Semantic-Aware Flowcited by 6
  5. 2025Point Prompting: Counterfactual Tracking with Video Diffusion Modelscited by 5
  6. 2023UFD-PRiME: Unsupervised Joint Learning of Optical Flow and Stereo Depth through Pixel-Level Rigid Motion Estimationcited by 1
  7. 2025Collaborative Unlabeled Data Optimizationcited by 0
  8. 2026GenOpticalFlow: A Generative Approach to Unsupervised Optical Flow Learningcited by 0
  9. 2026U2Flow: Uncertainty-Aware Unsupervised Optical Flow Estimationcited by 0
  10. 2026The TIME Machine: On The Power of Motion for Efficient Perceptioncited by 0