# MirrorFlow: Exploiting Symmetries in Joint Optical Flow and Occlusion Estimation

arXiv: https://arxiv.org/abs/1708.05355 · HTML: https://mlsanity.com/paper/1708.05355/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Aug 2017.

## Built on by (most cited first, 21 of 21)

- [Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans](https://mlsanity.com/paper/2110.04994/) (2021)
- [Learning to Estimate Hidden Motions with Global Motion Aggregation](https://mlsanity.com/paper/2104.02409/) (2021)
- [The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation](https://mlsanity.com/paper/2306.01923/) (2023)
- [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)
- [Learning Facial Representations from the Cycle-consistency of Face](https://mlsanity.com/paper/2108.03427/) (2021)
- [Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point Clouds](https://mlsanity.com/paper/2104.04724/) (2021)
- [Gaze-VLM:Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding](https://mlsanity.com/paper/2510.21356/) (2025)
- [Self-Supervised Any-Point Tracking by Contrastive Random Walks](https://mlsanity.com/paper/2409.16288/) (2024)
- [Adverse Weather Optical Flow: Cumulative Homogeneous-Heterogeneous Adaptation](https://mlsanity.com/paper/2409.17001/) (2024)
- [Towards Saner Deep Image Registration](https://mlsanity.com/paper/2307.09696/) (2023)
- [Stereo Matching with Cost Volume based Sparse Disparity Propagation](https://mlsanity.com/paper/2201.11937/) (2022)
- [YOIO: You Only Iterate Once by mining and fusing multiple necessary global information in the optical flow estimation](https://mlsanity.com/paper/2401.05879/) (2024)
- [Temporally Coherent Person Matting Trained on Fake-Motion Dataset](https://mlsanity.com/paper/2109.04843/) (2021)
- [Learning Omnidirectional Flow in 360-degree Video via Siamese Representation](https://mlsanity.com/paper/2208.03620/) (2022)
- [INV-Flow2PoseNet: Light-Resistant Rigid Object Pose from Optical Flow of RGB-D Images using Images, Normals and Vertices](https://mlsanity.com/paper/2209.06562/) (2022)
- [Optical Flow Estimation in 360^circ Videos: Dataset, Model and Application](https://mlsanity.com/paper/2301.11880/) (2023)
- [Trustworthy Self-Attention: Enabling the Network to Focus Only on the Most Relevant References](https://mlsanity.com/paper/2403.00211/) (2024)
- [Rethink Predicting the Optical Flow with the Kinetics Perspective](https://mlsanity.com/paper/2405.12512/) (2024)
- [Flow-CDNet: A Novel Network for Detecting Both Slow and Fast Changes in Bitemporal Images](https://mlsanity.com/paper/2507.02307/) (2025)
- [Gaze-Regularized VLMs for Ego-Centric Behavior Understanding](https://mlsanity.com/paper/2603.23190/) (2026)

## Abstract (arXiv)

Optical flow estimation is one of the most studied problems in computer vision, yet recent benchmark datasets continue to reveal problem areas of today's approaches. Occlusions have remained one of the key challenges. In this paper, we propose a symmetric optical flow method to address the well-known chicken-and-egg relation between optical flow and occlusions. In contrast to many state-of-the-art methods that consider occlusions as outliers, possibly filtered out during post-processing, we highlight the importance of joint occlusion reasoning in the optimization and show how to utilize occlusion as an important cue for estimating optical flow. The key feature of our model is to fully exploit the symmetry properties that characterize optical flow and occlusions in the two consecutive images. Specifically through utilizing forward-backward consistency and occlusion-disocclusion symmetry in the energy, our model jointly estimates optical flow in both forward and backward direction, as well as consistent occlusion maps in both views. We demonstrate significant performance benefits on standard benchmarks, especially from the occlusion-disocclusion symmetry. On the challenging KITTI dataset we report the most accurate two-frame results to date.