# Occlusion Aware Unsupervised Learning of Optical Flow

arXiv: https://arxiv.org/abs/1711.05890 · HTML: https://mlsanity.com/paper/1711.05890/

## Key facts

- Cited by 101 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2017.

## Built on by (most cited first, 30 of 101)

- [Learning to Estimate Hidden Motions with Global Motion Aggregation](https://mlsanity.com/paper/2104.02409/) (2021)
- [Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos](https://mlsanity.com/paper/2205.14065/) (2022)
- [CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos](https://mlsanity.com/paper/2410.11831/) (2024)
- [XVFI: eXtreme Video Frame Interpolation](https://mlsanity.com/paper/2103.16206/) (2021)
- [BootsTAP: Bootstrapped Training for Tracking-Any-Point](https://mlsanity.com/paper/2402.00847/) (2024)
- [SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping](https://mlsanity.com/paper/2105.07014/) (2021)
- [Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescue](https://mlsanity.com/paper/2112.08122/) (2021)
- [Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency](https://mlsanity.com/paper/2102.02629/) (2021)
- [Self-Supervised Pillar Motion Learning for Autonomous Driving](https://mlsanity.com/paper/2104.08683/) (2021)
- [Warp Consistency for Unsupervised Learning of Dense Correspondences](https://mlsanity.com/paper/2104.03308/) (2021)
- [Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation](https://mlsanity.com/paper/2207.07522/) (2022)
- [Learning Pixel Trajectories with Multiscale Contrastive Random Walks](https://mlsanity.com/paper/2201.08379/) (2022)
- [Instance-wise Occlusion and Depth Orders in Natural Scenes](https://mlsanity.com/paper/2111.14562/) (2021)
- [MVPGS: Excavating Multi-view Priors for Gaussian Splatting from Sparse Input Views](https://mlsanity.com/paper/2409.14316/) (2024)
- [Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2110.08192/) (2021)
- [Event-Based Video Frame Interpolation With Cross-Modal Asymmetric Bidirectional Motion Fields](https://mlsanity.com/paper/2502.13716/) (2025)
- [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)
- [Generative Transformer for Accurate and Reliable Salient Object Detection](https://mlsanity.com/paper/2104.10127/) (2021)
- [VOLDOR: Visual Odometry from Log-logistic Dense Optical flow Residuals](https://mlsanity.com/paper/2104.06789/) (2021)
- [Comparing Correspondences: Video Prediction with Correspondence-wise Losses](https://mlsanity.com/paper/2104.09498/) (2021)
- [Overcoming Obstructions via Bandwidth-Limited Multi-Agent Spatial Handshaking](https://mlsanity.com/paper/2107.00771/) (2021)
- [GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning](https://mlsanity.com/paper/2103.13725/) (2021)
- [Learning Co-segmentation by Segment Swapping for Retrieval and Discovery](https://mlsanity.com/paper/2110.15904/) (2021)
- [Context-Aware Video Reconstruction for Rolling Shutter Cameras](https://mlsanity.com/paper/2205.12912/) (2022)
- [Unsupervised Deformable Image Registration with Absent Correspondences in Pre-operative and Post-Recurrence Brain Tumor MRI Scans](https://mlsanity.com/paper/2206.03900/) (2022)
- [Optical Flow Training under Limited Label Budget via Active Learning](https://mlsanity.com/paper/2203.05053/) (2022)
- [Position-Aware Relation Learning for RGB-Thermal Salient Object Detection](https://mlsanity.com/paper/2209.10158/) (2022)
- [Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point Clouds](https://mlsanity.com/paper/2104.04724/) (2021)
- [Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration](https://mlsanity.com/paper/2205.10195/) (2022)

## Abstract (arXiv)

It has been recently shown that a convolutional neural network can learn optical flow estimation with unsupervised learning. However, the performance of the unsupervised methods still has a relatively large gap compared to its supervised counterpart. Occlusion and large motion are some of the major factors that limit the current unsupervised learning of optical flow methods. In this work we introduce a new method which models occlusion explicitly and a new warping way that facilitates the learning of large motion. Our method shows promising results on Flying Chairs, MPI-Sintel and KITTI benchmark datasets. Especially on KITTI dataset where abundant unlabeled samples exist, our unsupervised method outperforms its counterpart trained with supervised learning.