mlsanityData to 7 Oct 2026

DDFlow: Learning Optical Flow with Unlabeled Data Distillation

arXiv 1902.09145 ↗First posted 25 Feb 2019cs.CVcited by 63

Not on the map. Why?

Abstract (arXiv)

We present DDFlow, a data distillation approach to learning optical flow estimation from unlabeled data. The approach distills reliable predictions from a teacher network, and uses these predictions as annotations to guide a student network to learn optical flow. Unlike existing work relying on hand-crafted energy terms to handle occlusion, our approach is data-driven, and learns optical flow for occluded pixels. This enables us to train our model with a much simpler loss function, and achieve a much higher accuracy. We conduct a rigorous evaluation on the challenging Flying Chairs, MPI Sintel, KITTI 2012 and 2015 benchmarks, and show that our approach significantly outperforms all existing unsupervised learning methods, while running at real time.

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 17; 2023: 11; 2024: 9; 2025: 4; 2026: 4.

63 papers.

Sort:

By area:

  1. 2024CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videoscited by 122
  2. 2024BootsTAP: Bootstrapped Training for Tracking-Any-Pointcited by 115
  3. 2022IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolationcited by 107
  4. 2021PDC-Net+: Enhanced Probabilistic Dense Correspondence Networkcited by 80
  5. 2021SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warpingcited by 74
  6. 2023MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Featurescited by 53
  7. 2021Warp Consistency for Unsupervised Learning of Dense Correspondencescited by 42
  8. 2022Learning Pixel Trajectories with Multiscale Contrastive Random Walkscited by 36
  9. 2021Self-Supervised Multi-Frame Monocular Scene Flowcited by 29
  10. 2021Learning optical flow from still imagescited by 28
  11. 2022Imposing Consistency for Optical Flow Estimationcited by 24
  12. 2022RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videoscited by 22
38 more
  1. 2021Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistencycited by 19
  2. 2023Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillationcited by 19
  3. 2021Comparing Correspondences: Video Prediction with Correspondence-wise Lossescited by 16
  4. 2022Semi-Supervised Learning of Semantic Correspondence with Pseudo-Labelscited by 16
  5. 2021GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learningcited by 15
  6. 2022Spatial-then-Temporal Self-Supervised Learning for Video Correspondencecited by 13
  7. 2021Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point Cloudscited by 11
  8. 2021Learning Contrastive Representation for Semantic Correspondencecited by 11
  9. 2024PooDLe: Pooled and dense self-supervised learning from naturalistic videoscited by 11
  10. 2022MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillationcited by 10
  11. 2022Self-supervised AutoFlowcited by 10
  12. 2023GyroFlow+: Gyroscope-Guided Unsupervised Deep Homography and Optical Flow Learningcited by 10
  13. 2023Self-Supervised Motion Magnification by Backpropagating Through Optical Flowcited by 10
  14. 2024Self-Supervised Any-Point Tracking by Contrastive Random Walkscited by 10
  15. 2023SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Drivingcited by 9
  16. 2023Unsupervised Cumulative Domain Adaptation for Foggy Scene Optical Flowcited by 9
  17. 2025Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Imagescited by 9
  18. 2021ASFlow: Unsupervised Optical Flow Learning with Adaptive Pyramid Samplingcited by 8
  19. 2022SuperWarp: Supervised Learning and Warping on U-Net for Invariant Subvoxel-Precise Registrationcited by 8
  20. 2022Learning Depth from Focus in the Wildcited by 8
  21. 2023DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volumecited by 8
  22. 2024UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Modelcited by 8
  23. 2021The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Imagecited by 7
  24. 2022Unsupervised Learning of 3D Scene Flow from Monocular Cameracited by 7
  25. 2022GlobalFlowNet: Video Stabilization using Deep Distilled Global Motion Estimatescited by 7
  26. 2021LIFE: Lighting Invariant Flow Estimationcited by 6
  27. 2021Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimationcited by 6
  28. 2024LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectivescited by 6
  29. 2025Instance-Level Moving Object Segmentation from a Single Image with Eventscited by 6
  30. 2025Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Scene Optical Flowcited by 5
  31. 2021Sensor-Guided Optical Flowcited by 4
  32. 2022Box Supervised Video Segmentation Proposal Networkcited by 4
  33. 2022Learning to Estimate and Refine Fluid Motion with Physical Dynamicscited by 4
  34. 2024Adverse Weather Optical Flow: Cumulative Homogeneous-Heterogeneous Adaptationcited by 4
  35. 2021NccFlow: Unsupervised Learning of Optical Flow With Non-occlusion from Geometrycited by 3
  36. 2023Unsupervised Hierarchical Domain Adaptation for Adverse Weather Optical Flowcited by 3
  37. 2021Unsupervised Motion Representation Enhanced Network for Action Recognitioncited by 2
  38. 2023Unsupervised Learning Optical Flow in Multi-frame Dynamic Environment Using Temporal Dynamic Modelingcited by 2

50 most cited of 63 All 63 (JSON)