# DDFlow: Learning Optical Flow with Unlabeled Data Distillation

arXiv: https://arxiv.org/abs/1902.09145 · HTML: https://mlsanity.com/paper/1902.09145/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Feb 2019.

## Built on by (most cited first, 30 of 63)

- [CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos](https://mlsanity.com/paper/2410.11831/) (2024)
- [BootsTAP: Bootstrapped Training for Tracking-Any-Point](https://mlsanity.com/paper/2402.00847/) (2024)
- [IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation](https://mlsanity.com/paper/2205.14620/) (2022)
- [PDC-Net+: Enhanced Probabilistic Dense Correspondence Network](https://mlsanity.com/paper/2109.13912/) (2021)
- [SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping](https://mlsanity.com/paper/2105.07014/) (2021)
- [MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Features](https://mlsanity.com/paper/2307.12698/) (2023)
- [Warp Consistency for Unsupervised Learning of Dense Correspondences](https://mlsanity.com/paper/2104.03308/) (2021)
- [Learning Pixel Trajectories with Multiscale Contrastive Random Walks](https://mlsanity.com/paper/2201.08379/) (2022)
- [Self-Supervised Multi-Frame Monocular Scene Flow](https://mlsanity.com/paper/2105.02216/) (2021)
- [Learning optical flow from still images](https://mlsanity.com/paper/2104.03965/) (2021)
- [Imposing Consistency for Optical Flow Estimation](https://mlsanity.com/paper/2204.07262/) (2022)
- [RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos](https://mlsanity.com/paper/2207.11075/) (2022)
- [Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillation](https://mlsanity.com/paper/2306.10687/) (2023)
- [Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency](https://mlsanity.com/paper/2103.12886/) (2021)
- [Comparing Correspondences: Video Prediction with Correspondence-wise Losses](https://mlsanity.com/paper/2104.09498/) (2021)
- [Semi-Supervised Learning of Semantic Correspondence with Pseudo-Labels](https://mlsanity.com/paper/2203.16038/) (2022)
- [GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning](https://mlsanity.com/paper/2103.13725/) (2021)
- [Spatial-then-Temporal Self-Supervised Learning for Video Correspondence](https://mlsanity.com/paper/2209.07778/) (2022)
- [Learning Contrastive Representation for Semantic Correspondence](https://mlsanity.com/paper/2109.10967/) (2021)
- [Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point Clouds](https://mlsanity.com/paper/2104.04724/) (2021)
- [PooDLe: Pooled and dense self-supervised learning from naturalistic videos](https://mlsanity.com/paper/2408.11208/) (2024)
- [MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation](https://mlsanity.com/paper/2211.06018/) (2022)
- [Self-supervised AutoFlow](https://mlsanity.com/paper/2212.01762/) (2022)
- [GyroFlow+: Gyroscope-Guided Unsupervised Deep Homography and Optical Flow Learning](https://mlsanity.com/paper/2301.10018/) (2023)
- [Self-Supervised Motion Magnification by Backpropagating Through Optical Flow](https://mlsanity.com/paper/2311.17056/) (2023)
- [Self-Supervised Any-Point Tracking by Contrastive Random Walks](https://mlsanity.com/paper/2409.16288/) (2024)
- [SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Driving](https://mlsanity.com/paper/2303.06209/) (2023)
- [Unsupervised Cumulative Domain Adaptation for Foggy Scene Optical Flow](https://mlsanity.com/paper/2303.07564/) (2023)
- [Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images](https://mlsanity.com/paper/2506.07740/) (2025)
- [ASFlow: Unsupervised Optical Flow Learning with Adaptive Pyramid Sampling](https://mlsanity.com/paper/2104.03560/) (2021)

## 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.