StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation
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_ | 1866912757857648640 |
|---|---|
| author | Xing, Ke Jin, Xiaojie Li, Longfei Yin, Yuyang Liang, Hanwen Luo, Guixun Fang, Chen Wang, Jue Plataniotis, Konstantinos N. Zhao, Yao Wei, Yunchao |
| author_facet | Xing, Ke Jin, Xiaojie Li, Longfei Yin, Yuyang Liang, Hanwen Luo, Guixun Fang, Chen Wang, Jue Plataniotis, Konstantinos N. Zhao, Yao Wei, Yunchao |
| contents | The growing adoption of XR devices has fueled strong demand for high-quality stereo video, yet its production remains costly and artifact-prone. To address this challenge, we present StereoWorld, an end-to-end framework that repurposes a pretrained video generator for high-fidelity monocular-to-stereo video generation. Our framework jointly conditions the model on the monocular video input while explicitly supervising the generation with a geometry-aware regularization to ensure 3D structural fidelity. A spatio-temporal tiling scheme is further integrated to enable efficient, high-resolution synthesis. To enable large-scale training and evaluation, we curate a high-definition stereo video dataset containing over 11M frames aligned to natural human interpupillary distance (IPD). Extensive experiments demonstrate that StereoWorld substantially outperforms prior methods, generating stereo videos with superior visual fidelity and geometric consistency. The project webpage is available at https://ke-xing.github.io/StereoWorld/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_09363 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation Xing, Ke Jin, Xiaojie Li, Longfei Yin, Yuyang Liang, Hanwen Luo, Guixun Fang, Chen Wang, Jue Plataniotis, Konstantinos N. Zhao, Yao Wei, Yunchao Computer Vision and Pattern Recognition The growing adoption of XR devices has fueled strong demand for high-quality stereo video, yet its production remains costly and artifact-prone. To address this challenge, we present StereoWorld, an end-to-end framework that repurposes a pretrained video generator for high-fidelity monocular-to-stereo video generation. Our framework jointly conditions the model on the monocular video input while explicitly supervising the generation with a geometry-aware regularization to ensure 3D structural fidelity. A spatio-temporal tiling scheme is further integrated to enable efficient, high-resolution synthesis. To enable large-scale training and evaluation, we curate a high-definition stereo video dataset containing over 11M frames aligned to natural human interpupillary distance (IPD). Extensive experiments demonstrate that StereoWorld substantially outperforms prior methods, generating stereo videos with superior visual fidelity and geometric consistency. The project webpage is available at https://ke-xing.github.io/StereoWorld/. |
| title | StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.09363 |