ZeroStereo: Zero-shot Stereo Matching from Single Images
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913963181080576 |
|---|---|
| author | Wang, Xianqi Yang, Hao Xu, Gangwei Cheng, Junda Lin, Min Deng, Yong Zang, Jinliang Chen, Yurui Yang, Xin |
| author_facet | Wang, Xianqi Yang, Hao Xu, Gangwei Cheng, Junda Lin, Min Deng, Yong Zang, Jinliang Chen, Yurui Yang, Xin |
| contents | State-of-the-art supervised stereo matching methods have achieved remarkable performance on various benchmarks. However, their generalization to real-world scenarios remains challenging due to the scarcity of annotated real-world stereo data. In this paper, we propose ZeroStereo, a novel stereo image generation pipeline for zero-shot stereo matching. Our approach synthesizes high-quality right images from arbitrary single images by leveraging pseudo disparities generated by a monocular depth estimation model. Unlike previous methods that address occluded regions by filling missing areas with neighboring pixels or random backgrounds, we fine-tune a diffusion inpainting model to recover missing details while preserving semantic structure. Additionally, we propose Training-Free Confidence Generation, which mitigates the impact of unreliable pseudo labels without additional training, and Adaptive Disparity Selection, which ensures a diverse and realistic disparity distribution while preventing excessive occlusion and foreground distortion. Experiments demonstrate that models trained with our pipeline achieve state-of-the-art zero-shot generalization across multiple datasets with only a dataset volume comparable to Scene Flow. Code: https://github.com/Windsrain/ZeroStereo. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_08654 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ZeroStereo: Zero-shot Stereo Matching from Single Images Wang, Xianqi Yang, Hao Xu, Gangwei Cheng, Junda Lin, Min Deng, Yong Zang, Jinliang Chen, Yurui Yang, Xin Computer Vision and Pattern Recognition State-of-the-art supervised stereo matching methods have achieved remarkable performance on various benchmarks. However, their generalization to real-world scenarios remains challenging due to the scarcity of annotated real-world stereo data. In this paper, we propose ZeroStereo, a novel stereo image generation pipeline for zero-shot stereo matching. Our approach synthesizes high-quality right images from arbitrary single images by leveraging pseudo disparities generated by a monocular depth estimation model. Unlike previous methods that address occluded regions by filling missing areas with neighboring pixels or random backgrounds, we fine-tune a diffusion inpainting model to recover missing details while preserving semantic structure. Additionally, we propose Training-Free Confidence Generation, which mitigates the impact of unreliable pseudo labels without additional training, and Adaptive Disparity Selection, which ensures a diverse and realistic disparity distribution while preventing excessive occlusion and foreground distortion. Experiments demonstrate that models trained with our pipeline achieve state-of-the-art zero-shot generalization across multiple datasets with only a dataset volume comparable to Scene Flow. Code: https://github.com/Windsrain/ZeroStereo. |
| title | ZeroStereo: Zero-shot Stereo Matching from Single Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.08654 |