Procedural Dataset Generation for Zero-Shot Stereo Matching

Synthetic datasets are a crucial ingredient for training stereo matching networks, but the question of what makes a stereo dataset effective remains largely unexplored. We investigate the design space of synthetic datasets by varying the parameters of a procedural dataset generator, and report the effects on zero-shot stereo matching performance using standard benchmarks. We collect the best settings to produce Infinigen-Stereo, a procedural generator specifically optimized for zero-shot stereo datasets. Models trained only on data from our system outperform robust baselines trained on a combination of existing synthetic datasets and have stronger zero-shot stereo matching performance than public checkpoints from prior works. We open source our system atthis https URLto enable further research on procedural stereo datasets.

@article{yan2025_2504.16930,
  title={ Procedural Dataset Generation for Zero-Shot Stereo Matching },
  author={ David Yan and Alexander Raistrick and Jia Deng },
  journal={arXiv preprint arXiv:2504.16930},
  year={ 2025 }
}