FreeTimeGS: Free Gaussian Primitives at Anytime and Anywhere for Dynamic Scene Reconstruction
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_ | 1866915330360606720 |
|---|---|
| author | Wang, Yifan Yang, Peishan Xu, Zhen Sun, Jiaming Zhang, Zhanhua Chen, Yong Bao, Hujun Peng, Sida Zhou, Xiaowei |
| author_facet | Wang, Yifan Yang, Peishan Xu, Zhen Sun, Jiaming Zhang, Zhanhua Chen, Yong Bao, Hujun Peng, Sida Zhou, Xiaowei |
| contents | This paper addresses the challenge of reconstructing dynamic 3D scenes with complex motions. Some recent works define 3D Gaussian primitives in the canonical space and use deformation fields to map canonical primitives to observation spaces, achieving real-time dynamic view synthesis. However, these methods often struggle to handle scenes with complex motions due to the difficulty of optimizing deformation fields. To overcome this problem, we propose FreeTimeGS, a novel 4D representation that allows Gaussian primitives to appear at arbitrary time and locations. In contrast to canonical Gaussian primitives, our representation possesses the strong flexibility, thus improving the ability to model dynamic 3D scenes. In addition, we endow each Gaussian primitive with an motion function, allowing it to move to neighboring regions over time, which reduces the temporal redundancy. Experiments results on several datasets show that the rendering quality of our method outperforms recent methods by a large margin. Project page: https://zju3dv.github.io/freetimegs/ . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_05348 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FreeTimeGS: Free Gaussian Primitives at Anytime and Anywhere for Dynamic Scene Reconstruction Wang, Yifan Yang, Peishan Xu, Zhen Sun, Jiaming Zhang, Zhanhua Chen, Yong Bao, Hujun Peng, Sida Zhou, Xiaowei Computer Vision and Pattern Recognition This paper addresses the challenge of reconstructing dynamic 3D scenes with complex motions. Some recent works define 3D Gaussian primitives in the canonical space and use deformation fields to map canonical primitives to observation spaces, achieving real-time dynamic view synthesis. However, these methods often struggle to handle scenes with complex motions due to the difficulty of optimizing deformation fields. To overcome this problem, we propose FreeTimeGS, a novel 4D representation that allows Gaussian primitives to appear at arbitrary time and locations. In contrast to canonical Gaussian primitives, our representation possesses the strong flexibility, thus improving the ability to model dynamic 3D scenes. In addition, we endow each Gaussian primitive with an motion function, allowing it to move to neighboring regions over time, which reduces the temporal redundancy. Experiments results on several datasets show that the rendering quality of our method outperforms recent methods by a large margin. Project page: https://zju3dv.github.io/freetimegs/ . |
| title | FreeTimeGS: Free Gaussian Primitives at Anytime and Anywhere for Dynamic Scene Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.05348 |