# Learning to Adapt for Stereo

arXiv: https://arxiv.org/abs/1904.02957 · HTML: https://mlsanity.com/paper/1904.02957/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Apr 2019.

## Built on by (most cited first, 30 of 42)

- [SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation](https://mlsanity.com/paper/2206.08367/) (2022)
- [NeRF-Supervised Deep Stereo](https://mlsanity.com/paper/2303.17603/) (2023)
- [GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Feature](https://mlsanity.com/paper/2204.00179/) (2022)
- [Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction](https://mlsanity.com/paper/2103.16449/) (2021)
- [ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networks](https://mlsanity.com/paper/2201.02263/) (2022)
- [Test-Time Training on Video Streams](https://mlsanity.com/paper/2307.05014/) (2023)
- [Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation](https://mlsanity.com/paper/2111.04017/) (2021)
- [On the confidence of stereo matching in a deep-learning era: a quantitative evaluation](https://mlsanity.com/paper/2101.00431/) (2021)
- [On the Road to Online Adaptation for Semantic Image Segmentation](https://mlsanity.com/paper/2203.16195/) (2022)
- [Neural Disparity Refinement for Arbitrary Resolution Stereo](https://mlsanity.com/paper/2110.15367/) (2021)
- [One to Many: Adaptive Instrument Segmentation via Meta Learning and Dynamic Online Adaptation in Robotic Surgical Video](https://mlsanity.com/paper/2103.12988/) (2021)
- [Stereo Matching by Self-supervision of Multiscopic Vision](https://mlsanity.com/paper/2104.04170/) (2021)
- [Federated Online Adaptation for Deep Stereo](https://mlsanity.com/paper/2405.14873/) (2024)
- [Diving into the Fusion of Monocular Priors for Generalized Stereo Matching](https://mlsanity.com/paper/2505.14414/) (2025)
- [Active Stereo Without Pattern Projector](https://mlsanity.com/paper/2309.12315/) (2023)
- [Stereo Risk: A Continuous Modeling Approach to Stereo Matching](https://mlsanity.com/paper/2407.03152/) (2024)
- [Towards Open-World Generation of Stereo Images and Unsupervised Matching](https://mlsanity.com/paper/2503.12720/) (2025)
- [Self-Improving Semantic Perception for Indoor Localisation](https://mlsanity.com/paper/2105.01595/) (2021)
- [PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation](https://mlsanity.com/paper/2207.13340/) (2022)
- [StereoFlowGAN: Co-training for Stereo and Flow with Unsupervised Domain Adaptation](https://mlsanity.com/paper/2309.01842/) (2023)
- [Meta-Optimization for Higher Model Generalizability in Single-Image Depth Prediction](https://mlsanity.com/paper/2305.07269/) (2023)
- [Reusable Architecture Growth for Continual Stereo Matching](https://mlsanity.com/paper/2404.00360/) (2024)
- [Towards Continual, Online, Self-Supervised Depth](https://mlsanity.com/paper/2103.00369/) (2021)
- [Geometry-Aware Unsupervised Domain Adaptation for Stereo Matching](https://mlsanity.com/paper/2103.14333/) (2021)
- [Achieving Domain Robustness in Stereo Matching Networks by Removing Shortcut Learning](https://mlsanity.com/paper/2106.08486/) (2021)
- [Boosting Generalizability towards Zero-Shot Cross-Dataset Single-Image Indoor Depth by Meta-Initialization](https://mlsanity.com/paper/2409.02486/) (2024)
- [Event Stream-based Visual Object Tracking: HDETrack V2 and A High-Definition Benchmark](https://mlsanity.com/paper/2502.05574/) (2025)
- [Online Test-time Adaptation for 3D Human Pose Estimation: A Practical Perspective with Estimated 2D Poses](https://mlsanity.com/paper/2503.11194/) (2025)
- [SpikeStereoNet: A Brain-Inspired Framework for Stereo Depth Estimation from Spike Streams](https://mlsanity.com/paper/2505.19487/) (2025)
- [RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereo](https://mlsanity.com/paper/2511.10107/) (2025)

## Abstract (arXiv)

Real world applications of stereo depth estimation require models that are robust to dynamic variations in the environment. Even though deep learning based stereo methods are successful, they often fail to generalize to unseen variations in the environment, making them less suitable for practical applications such as autonomous driving. In this work, we introduce a "learning-to-adapt" framework that enables deep stereo methods to continuously adapt to new target domains in an unsupervised manner. Specifically, our approach incorporates the adaptation procedure into the learning objective to obtain a base set of parameters that are better suited for unsupervised online adaptation. To further improve the quality of the adaptation, we learn a confidence measure that effectively masks the errors introduced during the unsupervised adaptation. We evaluate our method on synthetic and real-world stereo datasets and our experiments evidence that learning-to-adapt is, indeed beneficial for online adaptation on vastly different domains.