CamLit: Unified Video Diffusion with Explicit Camera and Lighting Control
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918389426946048 |
|---|---|
| author | Kuang, Zhiyi He, Chengan Zakharov, Egor Xue, Yuxuan Saito, Shunsuke Maury, Olivier Bagautdinov, Timur Zheng, Youyi Nam, Giljoo |
| author_facet | Kuang, Zhiyi He, Chengan Zakharov, Egor Xue, Yuxuan Saito, Shunsuke Maury, Olivier Bagautdinov, Timur Zheng, Youyi Nam, Giljoo |
| contents | We present CamLit, the first unified video diffusion model that jointly performs novel view synthesis (NVS) and relighting from a single input image. Given one reference image, a user-defined camera trajectory, and an environment map, CamLit synthesizes a video of the scene from new viewpoints under the specified illumination. Within a single generative process, our model produces temporally coherent and spatially aligned outputs, including relit novel-view frames and corresponding albedo frames, enabling high-quality control of both camera pose and lighting. Qualitative and quantitative experiments demonstrate that CamLit achieves high-fidelity outputs on par with state-of-the-art methods in both novel view synthesis and relighting, without sacrificing visual quality in either task. We show that a single generative model can effectively integrate camera and lighting control, simplifying the video generation pipeline while maintaining competitive performance and consistent realism. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_14241 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CamLit: Unified Video Diffusion with Explicit Camera and Lighting Control Kuang, Zhiyi He, Chengan Zakharov, Egor Xue, Yuxuan Saito, Shunsuke Maury, Olivier Bagautdinov, Timur Zheng, Youyi Nam, Giljoo Computer Vision and Pattern Recognition We present CamLit, the first unified video diffusion model that jointly performs novel view synthesis (NVS) and relighting from a single input image. Given one reference image, a user-defined camera trajectory, and an environment map, CamLit synthesizes a video of the scene from new viewpoints under the specified illumination. Within a single generative process, our model produces temporally coherent and spatially aligned outputs, including relit novel-view frames and corresponding albedo frames, enabling high-quality control of both camera pose and lighting. Qualitative and quantitative experiments demonstrate that CamLit achieves high-fidelity outputs on par with state-of-the-art methods in both novel view synthesis and relighting, without sacrificing visual quality in either task. We show that a single generative model can effectively integrate camera and lighting control, simplifying the video generation pipeline while maintaining competitive performance and consistent realism. |
| title | CamLit: Unified Video Diffusion with Explicit Camera and Lighting Control |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.14241 |