DynamicGS: Spatiotemporal Motion Distillation for Dynamic Scene Reconstruction with Gaussian Splatting
Computers · 19.11.2026 · 15 (11) · 854
DOI: 10.3390/computers15110854 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computers, online erschienen am 19.11.2026. Verfasst von Mingwei Cao und 3 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Anhui Province Higher Education Scientific Research Project.
Abstract (Originalsprache)
Dynamic scene reconstruction is essential for industrial vision and robotic perception, where accurate and efficient modeling of time-varying geometry is crucial for applications such as automated inspection, robotic manipulation, and autonomous navigation. 3D Gaussian Splatting (3DGS), with its explicit Gaussian primitives and efficient rasterization, offers an effective solution for high-quality, real-time scene reconstruction. However, existing 3DGS-based methods often rely on dense multi-view observations, making them vulnerable to geometric and temporal instability when only sparse views or monocular videos are available. In such settings, insufficient observations severely constrain Gaussian primitives, leading to inaccurate motion estimation, structural deformation, and temporal inconsistency. To address these challenges, we propose DynamicGS, a spatiotemporal motion distillation framework for dynamic scene reconstruction with Gaussian Splatting. The proposed DynamicGS explicitly models and regularizes Gaussian motion to improve the geometric stability and temporal consistency of reconstructed scenes. First, we introduce a canonical space and deformation field to represent the spatiotemporal evolution of dynamic scenes. Second, we design an explicit motion-aware representation to embed dynamic motion features into Gaussian primitives, enabling more effective modeling of time-varying geometry. Third, we develop a spatiotemporal motion distillation mechanism to constrain and refine Gaussian motion from a global perspective, reducing motion ambiguity and improving temporal coherence. Extensive experiments on D-NeRF and HyperNeRF datasets show that our DynamicGS outperforms other state-of-the-art methods and effectively improves both reconstruction quality and rendering efficiency for dynamic scenes.
Förderung
- National Natural Science Foundation of China
- Anhui Province Higher Education Scientific Research Project
Zitieren
APA
Cao, M., Liu, Z., Li, N., & Zhao, H. (2026). DynamicGS: Spatiotemporal Motion Distillation for Dynamic Scene Reconstruction with Gaussian Splatting. Computers, 15(11), 854. https://doi.org/10.3390/computers15110854
Vancouver
Cao M, Liu Z, Li N, Zhao H. DynamicGS: Spatiotemporal Motion Distillation for Dynamic Scene Reconstruction with Gaussian Splatting. Computers. 2026;15(11):854. doi:10.3390/computers15110854
BibTeX
@article{Cao2026,
author = {Cao, Mingwei and Liu, Zhihao and Li, Ning and Zhao, Haifeng},
title = {DynamicGS: Spatiotemporal Motion Distillation for Dynamic Scene Reconstruction with Gaussian Splatting},
journal = {Computers},
year = {2026},
volume = {15},
number = {11},
pages = {854},
doi = {10.3390/computers15110854}
}
EUVIMED