# PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation

arXiv: https://arxiv.org/abs/2207.13340 · HTML: https://mlsanity.com/paper/2207.13340/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 49 references that are in the map.
- First posted on arXiv 27 Jul 2022.

## Builds on (most cited first, 28 of 28)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [PointRend: Image Segmentation as Rendering](https://mlsanity.com/paper/1912.08193/) (2019)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [End-to-End Learning of Geometry and Context for Deep Stereo Regression](https://mlsanity.com/paper/1703.04309/) (2017)
- [RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching](https://mlsanity.com/paper/2109.07547/) (2021)
- [Virtual KITTI 2](https://mlsanity.com/paper/2001.10773/) (2020)
- [FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation](https://mlsanity.com/paper/1612.02649/) (2016)
- [Coupled Generative Adversarial Networks](https://mlsanity.com/paper/1606.07536/) (2016)
- [CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching](https://mlsanity.com/paper/2104.04314/) (2021)
- [Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches](https://mlsanity.com/paper/1510.05970/) (2015)
- [Online Meta-Learning](https://mlsanity.com/paper/1902.08438/) (2019)
- [HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching](https://mlsanity.com/paper/2007.12140/) (2020)
- [Domain-invariant Stereo Matching Networks](https://mlsanity.com/paper/1911.13287/) (2019)
- [StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction](https://mlsanity.com/paper/1807.08865/) (2018)
- [Real-time self-adaptive deep stereo](https://mlsanity.com/paper/1810.05424/) (2018)
- [Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2004.04398/) (2020)
- [Learning to Adapt for Stereo](https://mlsanity.com/paper/1904.02957/) (2019)
- [ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systems](https://mlsanity.com/paper/1807.06009/) (2018)
- [Continual Adaptation for Deep Stereo](https://mlsanity.com/paper/2007.05233/) (2020)
- [On the confidence of stereo matching in a deep-learning era: a quantitative evaluation](https://mlsanity.com/paper/2101.00431/) (2021)
- [Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains](https://mlsanity.com/paper/1803.06641/) (2018)
- [Online Adaptation through Meta-Learning for Stereo Depth Estimation](https://mlsanity.com/paper/1904.08462/) (2019)
- [Consistency Guided Scene Flow Estimation](https://mlsanity.com/paper/2006.11242/) (2020)

## Built on by (most cited first, 5 of 5)

- [Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail](https://mlsanity.com/paper/2412.04472/) (2024)
- [A Survey on Deep Stereo Matching in the Twenties](https://mlsanity.com/paper/2407.07816/) (2024)
- [Diving into the Fusion of Monocular Priors for Generalized Stereo Matching](https://mlsanity.com/paper/2505.14414/) (2025)
- [SABAF: Removing Strong Attribute Bias from Neural Networks with Adversarial Filtering](https://mlsanity.com/paper/2311.07141/) (2023)
- [RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereo](https://mlsanity.com/paper/2511.10107/) (2025)

## Abstract (arXiv)

Online stereo adaptation tackles the domain shift problem, caused by different environments between synthetic (training) and real (test) datasets, to promptly adapt stereo models in dynamic real-world applications such as autonomous driving. However, previous methods often fail to counteract particular regions related to dynamic objects with more severe environmental changes. To mitigate this issue, we propose to incorporate an auxiliary point-selective network into a meta-learning framework, called PointFix, to provide a robust initialization of stereo models for online stereo adaptation. In a nutshell, our auxiliary network learns to fix local variants intensively by effectively back-propagating local information through the meta-gradient for the robust initialization of the baseline model. This network is model-agnostic, so can be used in any kind of architectures in a plug-and-play manner. We conduct extensive experiments to verify the effectiveness of our method under three adaptation settings such as short-, mid-, and long-term sequences. Experimental results show that the proper initialization of the base stereo model by the auxiliary network enables our learning paradigm to achieve state-of-the-art performance at inference.