Efficient 4D Gaussian Stream with Low Rank Adaptation
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_ | 1866909506634514432 |
|---|---|
| author | Liu, Zhenhuan Liu, Shuai Lu, Yidong Chen, Yirui Yang, Jie Liu, Wei |
| author_facet | Liu, Zhenhuan Liu, Shuai Lu, Yidong Chen, Yirui Yang, Jie Liu, Wei |
| contents | Recent methods have made significant progress in synthesizing novel views with long video sequences. This paper proposes a highly scalable method for dynamic novel view synthesis with continual learning. We leverage the 3D Gaussians to represent the scene and a low-rank adaptation-based deformation model to capture the dynamic scene changes. Our method continuously reconstructs the dynamics with chunks of video frames, reduces the streaming bandwidth by $90\%$ while maintaining high rendering quality comparable to the off-line SOTA methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_16575 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient 4D Gaussian Stream with Low Rank Adaptation Liu, Zhenhuan Liu, Shuai Lu, Yidong Chen, Yirui Yang, Jie Liu, Wei Computer Vision and Pattern Recognition Recent methods have made significant progress in synthesizing novel views with long video sequences. This paper proposes a highly scalable method for dynamic novel view synthesis with continual learning. We leverage the 3D Gaussians to represent the scene and a low-rank adaptation-based deformation model to capture the dynamic scene changes. Our method continuously reconstructs the dynamics with chunks of video frames, reduces the streaming bandwidth by $90\%$ while maintaining high rendering quality comparable to the off-line SOTA methods. |
| title | Efficient 4D Gaussian Stream with Low Rank Adaptation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.16575 |