# Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenes

arXiv: https://arxiv.org/abs/1904.03848 · HTML: https://mlsanity.com/paper/1904.03848/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2019.

## Built on by (most cited first, 29 of 29)

- [Asymmetric Bilateral Motion Estimation for Video Frame Interpolation](https://mlsanity.com/paper/2108.06815/) (2021)
- [SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping](https://mlsanity.com/paper/2105.07014/) (2021)
- [Implicit Motion Handling for Video Camouflaged Object Detection](https://mlsanity.com/paper/2203.07363/) (2022)
- [MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Features](https://mlsanity.com/paper/2307.12698/) (2023)
- [ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring](https://mlsanity.com/paper/2103.04260/) (2021)
- [Deep Two-View Structure-from-Motion Revisited](https://mlsanity.com/paper/2104.00556/) (2021)
- [R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras](https://mlsanity.com/paper/2308.14713/) (2023)
- [Improving Audio-Visual Segmentation with Bidirectional Generation](https://mlsanity.com/paper/2308.08288/) (2023)
- [Learning Pixel Trajectories with Multiscale Contrastive Random Walks](https://mlsanity.com/paper/2201.08379/) (2022)
- [BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation](https://mlsanity.com/paper/2304.02225/) (2023)
- [Vicinity Vision Transformer](https://mlsanity.com/paper/2206.10552/) (2022)
- [RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos](https://mlsanity.com/paper/2207.11075/) (2022)
- [VOLDOR: Visual Odometry from Log-logistic Dense Optical flow Residuals](https://mlsanity.com/paper/2104.06789/) (2021)
- [GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning](https://mlsanity.com/paper/2103.13725/) (2021)
- [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)
- [Deep Laparoscopic Stereo Matching with Transformers](https://mlsanity.com/paper/2207.12152/) (2022)
- [ASFlow: Unsupervised Optical Flow Learning with Adaptive Pyramid Sampling](https://mlsanity.com/paper/2104.03560/) (2021)
- [LIFE: Lighting Invariant Flow Estimation](https://mlsanity.com/paper/2104.03097/) (2021)
- [Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimation](https://mlsanity.com/paper/2106.04195/) (2021)
- [NccFlow: Unsupervised Learning of Optical Flow With Non-occlusion from Geometry](https://mlsanity.com/paper/2107.03610/) (2021)
- [Video Frame Interpolation with Transformer](https://mlsanity.com/paper/2205.07230/) (2022)
- [Unsupervised Learning Optical Flow in Multi-frame Dynamic Environment Using Temporal Dynamic Modeling](https://mlsanity.com/paper/2304.07159/) (2023)
- [Camouflaged Object Tracking: A Benchmark](https://mlsanity.com/paper/2408.13877/) (2024)
- [Self-Supervised Learning of Depth and Ego-Motion from Video by Alternative Training and Geometric Constraints from 3D to 2D](https://mlsanity.com/paper/2108.01980/) (2021)
- [Deep Planar Parallax for Monocular Depth Estimation](https://mlsanity.com/paper/2301.03178/) (2023)
- [Unsupervised Region-Growing Network for Object Segmentation in Atmospheric Turbulence](https://mlsanity.com/paper/2311.03572/) (2023)
- [MinNav: Minimalist Navigation Using Optical Flow For Active Tiny Aerial Robots](https://mlsanity.com/paper/2606.07813/) (2026)

## Abstract (arXiv)

Unsupervised deep learning for optical flow computation has achieved promising results. Most existing deep-net based methods rely on image brightness consistency and local smoothness constraint to train the networks. Their performance degrades at regions where repetitive textures or occlusions occur. In this paper, we propose Deep Epipolar Flow, an unsupervised optical flow method which incorporates global geometric constraints into network learning. In particular, we investigate multiple ways of enforcing the epipolar constraint in flow estimation. To alleviate a "chicken-and-egg" type of problem encountered in dynamic scenes where multiple motions may be present, we propose a low-rank constraint as well as a union-of-subspaces constraint for training. Experimental results on various benchmarking datasets show that our method achieves competitive performance compared with supervised methods and outperforms state-of-the-art unsupervised deep-learning methods.