Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry
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_ | 1866908409097355264 |
|---|---|
| author | Seo, Junyoung Han, Jisang Jung, Jaewoo Jin, Siyoon Lee, Joungbin Narihira, Takuya Fukuda, Kazumi Shibuya, Takashi Ahn, Donghoon Hu, Shoukang Kim, Seungryong Mitsufuji, Yuki |
| author_facet | Seo, Junyoung Han, Jisang Jung, Jaewoo Jin, Siyoon Lee, Joungbin Narihira, Takuya Fukuda, Kazumi Shibuya, Takashi Ahn, Donghoon Hu, Shoukang Kim, Seungryong Mitsufuji, Yuki |
| contents | We introduce Vid-CamEdit, a novel framework for video camera trajectory editing, enabling the re-synthesis of monocular videos along user-defined camera paths. This task is challenging due to its ill-posed nature and the limited multi-view video data for training. Traditional reconstruction methods struggle with extreme trajectory changes, and existing generative models for dynamic novel view synthesis cannot handle in-the-wild videos. Our approach consists of two steps: estimating temporally consistent geometry, and generative rendering guided by this geometry. By integrating geometric priors, the generative model focuses on synthesizing realistic details where the estimated geometry is uncertain. We eliminate the need for extensive 4D training data through a factorized fine-tuning framework that separately trains spatial and temporal components using multi-view image and video data. Our method outperforms baselines in producing plausible videos from novel camera trajectories, especially in extreme extrapolation scenarios on real-world footage. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_13697 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry Seo, Junyoung Han, Jisang Jung, Jaewoo Jin, Siyoon Lee, Joungbin Narihira, Takuya Fukuda, Kazumi Shibuya, Takashi Ahn, Donghoon Hu, Shoukang Kim, Seungryong Mitsufuji, Yuki Computer Vision and Pattern Recognition We introduce Vid-CamEdit, a novel framework for video camera trajectory editing, enabling the re-synthesis of monocular videos along user-defined camera paths. This task is challenging due to its ill-posed nature and the limited multi-view video data for training. Traditional reconstruction methods struggle with extreme trajectory changes, and existing generative models for dynamic novel view synthesis cannot handle in-the-wild videos. Our approach consists of two steps: estimating temporally consistent geometry, and generative rendering guided by this geometry. By integrating geometric priors, the generative model focuses on synthesizing realistic details where the estimated geometry is uncertain. We eliminate the need for extensive 4D training data through a factorized fine-tuning framework that separately trains spatial and temporal components using multi-view image and video data. Our method outperforms baselines in producing plausible videos from novel camera trajectories, especially in extreme extrapolation scenarios on real-world footage. |
| title | Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.13697 |