What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908854940336128 |
|---|---|
| author | Yan, David Raistrick, Alexander Deng, Jia |
| author_facet | Yan, David Raistrick, Alexander Deng, Jia |
| contents | Synthetic datasets are a crucial ingredient for training stereo matching networks, but the question of what makes a stereo dataset effective remains underexplored. 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 validate our findings by collecting the best settings and creating a large-scale dataset. Training only on this dataset achieves better performance than training on a mixture of widely used datasets, and is competitive with training on the FoundationStereo dataset, with the additional benefit of open-source generation code and an accompanying parameter analysis to enable further research. We open-source our system at https://github.com/princeton-vl/InfinigenStereo to enable further research on procedural stereo datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_16930 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching? Yan, David Raistrick, Alexander Deng, Jia Computer Vision and Pattern Recognition Synthetic datasets are a crucial ingredient for training stereo matching networks, but the question of what makes a stereo dataset effective remains underexplored. 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 validate our findings by collecting the best settings and creating a large-scale dataset. Training only on this dataset achieves better performance than training on a mixture of widely used datasets, and is competitive with training on the FoundationStereo dataset, with the additional benefit of open-source generation code and an accompanying parameter analysis to enable further research. We open-source our system at https://github.com/princeton-vl/InfinigenStereo to enable further research on procedural stereo datasets. |
| title | What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching? |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.16930 |