# Self-Supervised Learning for Stereo Matching with Self-Improving Ability

arXiv: https://arxiv.org/abs/1709.00930 · HTML: https://mlsanity.com/paper/1709.00930/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Sep 2017.

## Built on by (most cited first, 30 of 32)

- [The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth](https://mlsanity.com/paper/2104.14540/) (2021)
- [CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching](https://mlsanity.com/paper/2104.04314/) (2021)
- [DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Models](https://mlsanity.com/paper/2302.12231/) (2023)
- [SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping](https://mlsanity.com/paper/2105.07014/) (2021)
- [NeRF-Supervised Deep Stereo](https://mlsanity.com/paper/2303.17603/) (2023)
- [Deep Two-View Structure-from-Motion Revisited](https://mlsanity.com/paper/2104.00556/) (2021)
- [PVStereo: Pyramid Voting Module for End-to-End Self-Supervised Stereo Matching](https://mlsanity.com/paper/2103.07094/) (2021)
- [Vicinity Vision Transformer](https://mlsanity.com/paper/2206.10552/) (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)
- [H-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging Epipolar Geometry](https://mlsanity.com/paper/2104.11288/) (2021)
- [Federated Online Adaptation for Deep Stereo](https://mlsanity.com/paper/2405.14873/) (2024)
- [Deep Laparoscopic Stereo Matching with Transformers](https://mlsanity.com/paper/2207.12152/) (2022)
- [Active Stereo Without Pattern Projector](https://mlsanity.com/paper/2309.12315/) (2023)
- [ActiveZero: Mixed Domain Learning for Active Stereovision with Zero Annotation](https://mlsanity.com/paper/2112.02772/) (2021)
- [Disparity-based Stereo Image Compression with Aligned Cross-View Priors](https://mlsanity.com/paper/2212.00459/) (2022)
- [Doduo: Learning Dense Visual Correspondence from Unsupervised Semantic-Aware Flow](https://mlsanity.com/paper/2309.15110/) (2023)
- [Towards Open-World Generation of Stereo Images and Unsupervised Matching](https://mlsanity.com/paper/2503.12720/) (2025)
- [Degradation-agnostic Correspondence from Resolution-asymmetric Stereo](https://mlsanity.com/paper/2204.01429/) (2022)
- [UAMD-Net: A Unified Adaptive Multimodal Neural Network for Dense Depth Completion](https://mlsanity.com/paper/2204.07791/) (2022)
- [Self-Supervised Monocular Depth Estimation of Untextured Indoor Rotated Scenes](https://mlsanity.com/paper/2106.12958/) (2021)
- [L3C-Stereo: Lossless Compression for Stereo Images](https://mlsanity.com/paper/2108.09422/) (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)
- [Achieving Domain Robustness in Stereo Matching Networks by Removing Shortcut Learning](https://mlsanity.com/paper/2106.08486/) (2021)
- [Co-Teaching: An Ark to Unsupervised Stereo Matching](https://mlsanity.com/paper/2107.08186/) (2021)
- [USegScene: Unsupervised Learning of Depth, Optical Flow and Ego-Motion with Semantic Guidance and Coupled Networks](https://mlsanity.com/paper/2207.07469/) (2022)
- [Fine-tuning deep learning models for stereo matching using results from semi-global matching](https://mlsanity.com/paper/2205.14051/) (2022)
- [Active Stereo in the Wild through Virtual Pattern Projection](https://mlsanity.com/paper/2406.04345/) (2024)
- [Integrating Disparity Confidence Estimation into Relative Depth Prior-Guided Unsupervised Stereo Matching](https://mlsanity.com/paper/2508.01275/) (2025)

## Abstract (arXiv)

Exiting deep-learning based dense stereo matching methods often rely on ground-truth disparity maps as the training signals, which are however not always available in many situations. In this paper, we design a simple convolutional neural network architecture that is able to learn to compute dense disparity maps directly from the stereo inputs. Training is performed in an end-to-end fashion without the need of ground-truth disparity maps. The idea is to use image warping error (instead of disparity-map residuals) as the loss function to drive the learning process, aiming to find a depth-map that minimizes the warping error. While this is a simple concept well-known in stereo matching, to make it work in a deep-learning framework, many non-trivial challenges must be overcome, and in this work we provide effective solutions. Our network is self-adaptive to different unseen imageries as well as to different camera settings. Experiments on KITTI and Middlebury stereo benchmark datasets show that our method outperforms many state-of-the-art stereo matching methods with a margin, and at the same time significantly faster.