# Flow2Stereo: Effective Self-Supervised Learning of Optical Flow and Stereo Matching

arXiv: https://arxiv.org/abs/2004.02138 · HTML: https://mlsanity.com/paper/2004.02138/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Apr 2020.

## Built on by (most cited first, 30 of 36)

- [SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping](https://mlsanity.com/paper/2105.07014/) (2021)
- [Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency](https://mlsanity.com/paper/2102.02629/) (2021)
- [Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail](https://mlsanity.com/paper/2412.04472/) (2024)
- [Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walk](https://mlsanity.com/paper/2105.08248/) (2021)
- [SkyEye: Self-Supervised Bird's-Eye-View Semantic Mapping Using Monocular Frontal View Images](https://mlsanity.com/paper/2302.04233/) (2023)
- [PVStereo: Pyramid Voting Module for End-to-End Self-Supervised Stereo Matching](https://mlsanity.com/paper/2103.07094/) (2021)
- [A Survey on Deep Stereo Matching in the Twenties](https://mlsanity.com/paper/2407.07816/) (2024)
- [SelfD: Self-Learning Large-Scale Driving Policies From the Web](https://mlsanity.com/paper/2204.10320/) (2022)
- [Stereo Matching by Self-supervision of Multiscopic Vision](https://mlsanity.com/paper/2104.04170/) (2021)
- [ChiTransformer:Towards Reliable Stereo from Cues](https://mlsanity.com/paper/2203.04554/) (2022)
- [TemporalStereo: Efficient Spatial-Temporal Stereo Matching Network](https://mlsanity.com/paper/2211.13755/) (2022)
- [MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation](https://mlsanity.com/paper/2211.06018/) (2022)
- [FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases](https://mlsanity.com/paper/2509.05297/) (2025)
- [Two-in-One Depth: Bridging the Gap Between Monocular and Binocular Self-supervised Depth Estimation](https://mlsanity.com/paper/2309.00933/) (2023)
- [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)
- [EMatch: A Unified Framework for Event-based Optical Flow and Stereo Matching](https://mlsanity.com/paper/2407.21735/) (2024)
- [Sensor-Guided Optical Flow](https://mlsanity.com/paper/2109.15321/) (2021)
- [StereoFlowGAN: Co-training for Stereo and Flow with Unsupervised Domain Adaptation](https://mlsanity.com/paper/2309.01842/) (2023)
- [NccFlow: Unsupervised Learning of Optical Flow With Non-occlusion from Geometry](https://mlsanity.com/paper/2107.03610/) (2021)
- [DMS:Diffusion-Based Multi-Baseline Stereo Generation for Improving Self-Supervised Depth Estimation](https://mlsanity.com/paper/2508.13091/) (2025)
- [Student-Teacher Learning from Clean Inputs to Noisy Inputs](https://mlsanity.com/paper/2103.07600/) (2021)
- [RoSe: Robust Self-supervised Stereo Matching under Adverse Weather Conditions](https://mlsanity.com/paper/2509.19165/) (2025)
- [SMFormer: Empowering Self-supervised Stereo Matching via Foundation Models and Data Augmentation](https://mlsanity.com/paper/2604.10218/) (2026)
- [Co-Teaching: An Ark to Unsupervised Stereo Matching](https://mlsanity.com/paper/2107.08186/) (2021)
- [UFD-PRiME: Unsupervised Joint Learning of Optical Flow and Stereo Depth through Pixel-Level Rigid Motion Estimation](https://mlsanity.com/paper/2310.04712/) (2023)
- [Generating Superpixels for High-resolution Images with Decoupled Patch Calibration](https://mlsanity.com/paper/2108.08607/) (2021)
- [A Noncontact Technique for Wave Measurement Based on Thermal Stereography and Deep Learning](https://mlsanity.com/paper/2408.10670/) (2024)
- [Pseudo-Stereo Inputs: A Solution to the Occlusion Challenge in Self-Supervised Stereo Matching](https://mlsanity.com/paper/2410.02534/) (2024)
- [Integrating Disparity Confidence Estimation into Relative Depth Prior-Guided Unsupervised Stereo Matching](https://mlsanity.com/paper/2508.01275/) (2025)

## Abstract (arXiv)

In this paper, we propose a unified method to jointly learn optical flow and stereo matching. Our first intuition is stereo matching can be modeled as a special case of optical flow, and we can leverage 3D geometry behind stereoscopic videos to guide the learning of these two forms of correspondences. We then enroll this knowledge into the state-of-the-art self-supervised learning framework, and train one single network to estimate both flow and stereo. Second, we unveil the bottlenecks in prior self-supervised learning approaches, and propose to create a new set of challenging proxy tasks to boost performance. These two insights yield a single model that achieves the highest accuracy among all existing unsupervised flow and stereo methods on KITTI 2012 and 2015 benchmarks. More remarkably, our self-supervised method even outperforms several state-of-the-art fully supervised methods, including PWC-Net and FlowNet2 on KITTI 2012.