|国家预印本平台
首页|STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering

STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering

STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering

来源:Arxiv_logoArxiv
英文摘要

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.

Zehao Li、Hao Jiang、Yujun Cai、Jianing Chen、Baolong Bi、Shuqin Gao、Honglong Zhao、Yiwei Wang、Tianlu Mao、Zhaoqi Wang

信息科学、信息技术计算技术、计算机技术

Zehao Li,Hao Jiang,Yujun Cai,Jianing Chen,Baolong Bi,Shuqin Gao,Honglong Zhao,Yiwei Wang,Tianlu Mao,Zhaoqi Wang.STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering[EB/OL].(2025-05-28)[2025-06-08].https://arxiv.org/abs/2505.22400.点此复制

评论