STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering
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_ | 1866918037274230784 |
|---|---|
| author | Li, Zehao Jiang, Hao Cai, Yujun Chen, Jianing Bi, Baolong Gao, Shuqin Zhao, Honglong Wang, Yiwei Mao, Tianlu Wang, Zhaoqi |
| author_facet | Li, Zehao Jiang, Hao Cai, Yujun Chen, Jianing Bi, Baolong Gao, Shuqin Zhao, Honglong Wang, Yiwei Mao, Tianlu Wang, Zhaoqi |
| contents | Although dynamic scene reconstruction has long been a fundamental challenge in 3D vision, the recent emergence of 3D Gaussian Splatting (3DGS) offers a promising direction by enabling high-quality, real-time rendering through explicit Gaussian primitives. However, existing 3DGS-based methods for dynamic reconstruction often suffer from \textit{spatio-temporal incoherence} during initialization, where canonical Gaussians are constructed by aggregating observations from multiple frames without temporal distinction. This results in spatio-temporally entangled representations, making it difficult to model dynamic motion accurately. To overcome this limitation, we propose \textbf{STDR} (Spatio-Temporal Decoupling for Real-time rendering), a plug-and-play module that learns spatio-temporal probability distributions for each Gaussian. STDR introduces a spatio-temporal mask, a separated deformation field, and a consistency regularization to jointly disentangle spatial and temporal patterns. Extensive experiments demonstrate that incorporating our module into existing 3DGS-based dynamic scene reconstruction frameworks leads to notable improvements in both reconstruction quality and spatio-temporal consistency across synthetic and real-world benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_22400 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering Li, Zehao Jiang, Hao Cai, Yujun Chen, Jianing Bi, Baolong Gao, Shuqin Zhao, Honglong Wang, Yiwei Mao, Tianlu Wang, Zhaoqi Graphics Computer Vision and Pattern Recognition Although dynamic scene reconstruction has long been a fundamental challenge in 3D vision, the recent emergence of 3D Gaussian Splatting (3DGS) offers a promising direction by enabling high-quality, real-time rendering through explicit Gaussian primitives. However, existing 3DGS-based methods for dynamic reconstruction often suffer from \textit{spatio-temporal incoherence} during initialization, where canonical Gaussians are constructed by aggregating observations from multiple frames without temporal distinction. This results in spatio-temporally entangled representations, making it difficult to model dynamic motion accurately. To overcome this limitation, we propose \textbf{STDR} (Spatio-Temporal Decoupling for Real-time rendering), a plug-and-play module that learns spatio-temporal probability distributions for each Gaussian. STDR introduces a spatio-temporal mask, a separated deformation field, and a consistency regularization to jointly disentangle spatial and temporal patterns. Extensive experiments demonstrate that incorporating our module into existing 3DGS-based dynamic scene reconstruction frameworks leads to notable improvements in both reconstruction quality and spatio-temporal consistency across synthetic and real-world benchmarks. |
| title | STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.22400 |