The recent development of 3D Gaussian splatting (3DGS) has led to great interest in 4D dynamic spatial reconstruction. Existing approaches mainly rely on full-length multi-view videos, while there has been limited exploration of online reconstruction methods that enable on-the-fly training and per-timestep streaming. Current 3DGS-based streaming methods treat the Gaussian primitives uniformly and constantly renew the densified Gaussians. Thus, they overlook the difference between dynamic and static features and neglect the temporal continuity of the scene. To address these limitations, we propose a novel pipeline for iterative streamable 4D dynamic spatial reconstruction. It comprises three stages: a selective inheritance stage that retains priors from previous timesteps to preserve the temporal continuity, a dynamics-aware shift stage that distinguishes dynamic and static primitives and employs distinct strategies to optimize their movements, and an error-guided densification stage that efficiently identifies Gaussians requiring densification to accommodate emerging objects. Our method achieves state-of-the-art performance in online 4D reconstruction, demonstrating compact storage, the fastest on-the-fly training, and superior representation quality.
Building similarity graph...
Analyzing shared references across papers
Loading...
Zhening Liu
Yingdong Hu
Xinjie Zhang
Building similarity graph...
Analyzing shared references across papers
Loading...
Liu et al. (Wed,) studied this question.
www.synapsesocial.com/papers/69f5943c71405d493affefc6 — DOI: https://doi.org/10.1109/tvcg.2026.3688730