# Achieving Domain Robustness in Stereo Matching Networks by Removing Shortcut Learning

arXiv: https://arxiv.org/abs/2106.08486 · HTML: https://mlsanity.com/paper/2106.08486/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 57 references that are in the map.
- First posted on arXiv 15 Jun 2021.

## Builds on (most cited first, 30 of 37)

- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1812.07179/) (2018)
- [End-to-End Learning of Geometry and Context for Deep Stereo Regression](https://mlsanity.com/paper/1703.04309/) (2017)
- [Learning to Learn Single Domain Generalization](https://mlsanity.com/paper/2003.13216/) (2020)
- [GA-Net: Guided Aggregation Net for End-to-end Stereo Matching](https://mlsanity.com/paper/1904.06587/) (2019)
- [Group-wise Correlation Stereo Network](https://mlsanity.com/paper/1903.04025/) (2019)
- [AANet: Adaptive Aggregation Network for Efficient Stereo Matching](https://mlsanity.com/paper/2004.09548/) (2020)
- [Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/1906.06310/) (2019)
- [Hierarchical Deep Stereo Matching on High-resolution Images](https://mlsanity.com/paper/1912.06704/) (2019)
- [DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch](https://mlsanity.com/paper/1909.05845/) (2019)
- [Domain-invariant Stereo Matching Networks](https://mlsanity.com/paper/1911.13287/) (2019)
- [Hierarchical Discrete Distribution Decomposition for Match Density Estimation](https://mlsanity.com/paper/1812.06264/) (2018)
- [StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction](https://mlsanity.com/paper/1807.08865/) (2018)
- [SegStereo: Exploiting Semantic Information for Disparity Estimation](https://mlsanity.com/paper/1807.11699/) (2018)
- [Real-time self-adaptive deep stereo](https://mlsanity.com/paper/1810.05424/) (2018)
- [Domain Generalization via Multidomain Discriminant Analysis](https://mlsanity.com/paper/1907.11216/) (2019)
- [Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching](https://mlsanity.com/paper/1708.09204/) (2017)
- [Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching](https://mlsanity.com/paper/1909.03751/) (2019)
- [Automatic Shortcut Removal for Self-Supervised Representation Learning](https://mlsanity.com/paper/2002.08822/) (2020)
- [Learning to Adapt for Stereo](https://mlsanity.com/paper/1904.02957/) (2019)
- [Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation](https://mlsanity.com/paper/2008.07130/) (2020)
- [Self-Supervised Learning for Stereo Matching with Self-Improving Ability](https://mlsanity.com/paper/1709.00930/) (2017)
- [EdgeStereo: A Context Integrated Residual Pyramid Network for Stereo Matching](https://mlsanity.com/paper/1803.05196/) (2018)
- [Matching-space Stereo Networks for Cross-domain Generalization](https://mlsanity.com/paper/2010.07347/) (2020)

## Built on by (most cited first, 1 of 1)

- [Independent Samples, Correlated Variance A Learnable Cross-View Cue in Path-Traced Stereo Data](https://mlsanity.com/paper/2606.25483/) (2026)

## Abstract (arXiv)

Learning-based stereo matching and depth estimation networks currently excel on public benchmarks with impressive results. However, state-of-the-art networks often fail to generalize from synthetic imagery to more challenging real data domains. This paper is an attempt to uncover hidden secrets of achieving domain robustness and in particular, discovering the important ingredients of generalization success of stereo matching networks by analyzing the effect of synthetic image learning on real data performance. We provide evidence that demonstrates that learning of features in the synthetic domain by a stereo matching network is heavily influenced by two "shortcuts" presented in the synthetic data: (1) identical local statistics (RGB colour features) between matching pixels in the synthetic stereo images and (2) lack of realism in synthetic textures on 3D objects simulated in game engines. We will show that by removing such shortcuts, we can achieve domain robustness in the state-of-the-art stereo matching frameworks and produce a remarkable performance on multiple realistic datasets, despite the fact that the networks were trained on synthetic data, only. Our experimental results point to the fact that eliminating shortcuts from the synthetic data is key to achieve domain-invariant generalization between synthetic and real data domains.