# Robust Synthetic-to-Real Transfer for Stereo Matching arXiv: https://arxiv.org/abs/2403.07705 ยท HTML: https://mlsanity.com/paper/2403.07705/ ## Key facts - Cited by 15 papers in the map (data through 14 Oct 2026). - Builds on 39 of its 61 references that are in the map. - First posted on arXiv 12 Mar 2024. ## Builds on (most cited first, 30 of 39) - [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015) - [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019) - [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020) - [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020) - [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015) - [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018) - [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018) - [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017) - [Decoupled Knowledge Distillation](https://mlsanity.com/paper/2203.08679/) (2022) - [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) - [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) - [Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation](https://mlsanity.com/paper/2203.11483/) (2022) - [Iterative Geometry Encoding Volume for Stereo Matching](https://mlsanity.com/paper/2303.06615/) (2023) - [Hierarchical Neural Architecture Search for Deep Stereo Matching](https://mlsanity.com/paper/2010.13501/) (2020) - [CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching](https://mlsanity.com/paper/2104.04314/) (2021) - [Learning Depth with Convolutional Spatial Propagation Network](https://mlsanity.com/paper/1810.02695/) (2018) - [Attention Concatenation Volume for Accurate and Efficient Stereo Matching](https://mlsanity.com/paper/2203.02146/) (2022) - [Hierarchical Deep Stereo Matching on High-resolution Images](https://mlsanity.com/paper/1912.06704/) (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) - [There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average](https://mlsanity.com/paper/1806.05594/) (2018) - [Real-time self-adaptive deep stereo](https://mlsanity.com/paper/1810.05424/) (2018) - [Computing the Stereo Matching Cost with a Convolutional Neural Network](https://mlsanity.com/paper/1409.4326/) (2014) - [PCW-Net: Pyramid Combination and Warping Cost Volume for Stereo Matching](https://mlsanity.com/paper/2006.12797/) (2020) - [Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching](https://mlsanity.com/paper/1909.03751/) (2019) - [Open Challenges in Deep Stereo: the Booster Dataset](https://mlsanity.com/paper/2206.04671/) (2022) - [Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective](https://mlsanity.com/paper/2203.10887/) (2022) ## Built on by (most cited first, 15 of 15) - [CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularization](https://mlsanity.com/paper/2405.12110/) (2024) - [Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail](https://mlsanity.com/paper/2412.04472/) (2024) - [MVSAnywhere: Zero-Shot Multi-View Stereo](https://mlsanity.com/paper/2503.22430/) (2025) - [A Survey on Deep Stereo Matching in the Twenties](https://mlsanity.com/paper/2407.07816/) (2024) - [Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Experts](https://mlsanity.com/paper/2507.04631/) (2025) - [Motif Channel Opened in a White-Box: Stereo Matching via Motif Correlation Graph](https://mlsanity.com/paper/2411.12426/) (2024) - [Exploring the Potential of Synthetic Data to Replace Real Data](https://mlsanity.com/paper/2408.14559/) (2024) - [Multi-Label Stereo Matching for Transparent Scene Depth Estimation](https://mlsanity.com/paper/2505.14008/) (2025) - [Hadamard Attention Recurrent Transformer: A Strong Baseline for Stereo Matching Transformer](https://mlsanity.com/paper/2501.01023/) (2025) - [SR-Stereo & DAPE: Stepwise Regression and Pre-trained Edges for Practical Stereo Matching](https://mlsanity.com/paper/2406.06953/) (2024) - [RGB-Phase Speckle: Cross-Scene Stereo 3D Reconstruction via Wrapped Pre-Normalization](https://mlsanity.com/paper/2503.06125/) (2025) - [DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions](https://mlsanity.com/paper/2505.05091/) (2025) - [MAGIC: Learning from Visibility Asymmetry for Unsupervised Stereo Matching](https://mlsanity.com/paper/2508.10838/) (2025) - [STEREOFLOW: Progressive Stereo Matching with StereoDiT and Transition Flow Matching](https://mlsanity.com/paper/2607.19986/) (2026) - [StereoDiffuer: Diffusion-based Progressive Geometry Modeling with Saliency Attention Perception for Stereo Matching](https://mlsanity.com/paper/2608.21710/) (2026) ## Abstract (arXiv) With advancements in domain generalized stereo matching networks, models pre-trained on synthetic data demonstrate strong robustness to unseen domains. However, few studies have investigated the robustness after fine-tuning them in real-world scenarios, during which the domain generalization ability can be seriously degraded. In this paper, we explore fine-tuning stereo matching networks without compromising their robustness to unseen domains. Our motivation stems from comparing Ground Truth (GT) versus Pseudo Label (PL) for fine-tuning: GT degrades, but PL preserves the domain generalization ability. Empirically, we find the difference between GT and PL implies valuable information that can regularize networks during fine-tuning. We also propose a framework to utilize this difference for fine-tuning, consisting of a frozen Teacher, an exponential moving average (EMA) Teacher, and a Student network. The core idea is to utilize the EMA Teacher to measure what the Student has learned and dynamically improve GT and PL for fine-tuning. We integrate our framework with state-of-the-art networks and evaluate its effectiveness on several real-world datasets. Extensive experiments show that our method effectively preserves the domain generalization ability during fine-tuning.