# StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching

arXiv: https://arxiv.org/abs/2005.01927 · HTML: https://mlsanity.com/paper/2005.01927/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2020.

## Built on by (most cited first, 21 of 21)

- [GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Feature](https://mlsanity.com/paper/2204.00179/) (2022)
- [ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networks](https://mlsanity.com/paper/2201.02263/) (2022)
- [DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network](https://mlsanity.com/paper/2103.07893/) (2021)
- [A Survey on Deep Stereo Matching in the Twenties](https://mlsanity.com/paper/2407.07816/) (2024)
- [SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding](https://mlsanity.com/paper/2511.04668/) (2025)
- [Learning Intra-view and Cross-view Geometric Knowledge for Stereo Matching](https://mlsanity.com/paper/2402.19270/) (2024)
- [ActiveZero: Mixed Domain Learning for Active Stereovision with Zero Annotation](https://mlsanity.com/paper/2112.02772/) (2021)
- [AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach](https://mlsanity.com/paper/2112.04974/) (2021)
- [Semi-synthesis: A fast way to produce effective datasets for stereo matching](https://mlsanity.com/paper/2101.10811/) (2021)
- [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)
- [Degradation-agnostic Correspondence from Resolution-asymmetric Stereo](https://mlsanity.com/paper/2204.01429/) (2022)
- [StereoFlowGAN: Co-training for Stereo and Flow with Unsupervised Domain Adaptation](https://mlsanity.com/paper/2309.01842/) (2023)
- [Reusable Architecture Growth for Continual Stereo Matching](https://mlsanity.com/paper/2404.00360/) (2024)
- [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)
- [Image-to-Image Translation of Synthetic Samples for Rare Classes](https://mlsanity.com/paper/2106.12212/) (2021)
- [Online Adaptive Disparity Estimation for Dynamic Scenes in Structured Light Systems](https://mlsanity.com/paper/2310.08934/) (2023)
- [SyntStereo2Real: Edge-Aware GAN for Remote Sensing Image-to-Image Translation while Maintaining Stereo Constraint](https://mlsanity.com/paper/2404.09277/) (2024)
- [CMD: Constraining Multimodal Distribution for Domain Adaptation in Stereo Matching](https://mlsanity.com/paper/2504.21302/) (2025)
- [LDRNet: Large Deformation Registration Model for Chest CT Registration](https://mlsanity.com/paper/2602.01812/) (2026)

## Abstract (arXiv)

Large-scale synthetic datasets are beneficial to stereo matching but usually introduce known domain bias. Although unsupervised image-to-image translation networks represented by CycleGAN show great potential in dealing with domain gap, it is non-trivial to generalize this method to stereo matching due to the problem of pixel distortion and stereo mismatch after translation. In this paper, we propose an end-to-end training framework with domain translation and stereo matching networks to tackle this challenge. First, joint optimization between domain translation and stereo matching networks in our end-to-end framework makes the former facilitate the latter one to the maximum extent. Second, this framework introduces two novel losses, i.e., bidirectional multi-scale feature re-projection loss and correlation consistency loss, to help translate all synthetic stereo images into realistic ones as well as maintain epipolar constraints. The effective combination of above two contributions leads to impressive stereo-consistent translation and disparity estimation accuracy. In addition, a mode seeking regularization term is added to endow the synthetic-to-real translation results with higher fine-grained diversity. Extensive experiments demonstrate the effectiveness of the proposed framework on bridging the synthetic-to-real domain gap on stereo matching.