Fast and Robust Deformable 3D Gaussian Splatting

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Jiao, Han, Sun, Jiakai, Zhao, Lei, Zhang, Zhanjie, Xing, Wei, Lin, Huaizhong
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914413097779200
author Jiao, Han
Sun, Jiakai
Zhao, Lei
Zhang, Zhanjie
Xing, Wei
Lin, Huaizhong
author_facet Jiao, Han
Sun, Jiakai
Zhao, Lei
Zhang, Zhanjie
Xing, Wei
Lin, Huaizhong
contents 3D Gaussian Splatting has demonstrated remarkable real-time rendering capabilities and superior visual quality in novel view synthesis for static scenes. Building upon these advantages, researchers have progressively extended 3D Gaussians to dynamic scene reconstruction. Deformation field-based methods have emerged as a promising approach among various techniques. These methods maintain 3D Gaussian attributes in a canonical field and employ the deformation field to transform this field across temporal sequences. Nevertheless, these approaches frequently encounter challenges such as suboptimal rendering speeds, significant dependence on initial point clouds, and vulnerability to local optima in dim scenes. To overcome these limitations, we present FRoG, an efficient and robust framework for high-quality dynamic scene reconstruction. FRoG integrates per-Gaussian embedding with a coarse-to-fine temporal embedding strategy, accelerating rendering through the early fusion of temporal embeddings. Moreover, to enhance robustness against sparse initializations, we introduce a novel depth- and error-guided sampling strategy. This strategy populates the canonical field with new 3D Gaussians at low-deviation initial positions, significantly reducing the optimization burden on the deformation field and improving detail reconstruction in both static and dynamic regions. Furthermore, by modulating opacity variations, we mitigate the local optima problem in dim scenes, improving color fidelity. Comprehensive experimental results validate that our method achieves accelerated rendering speeds while maintaining state-of-the-art visual quality.
format Preprint
id arxiv_https___arxiv_org_abs_2603_20857
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Fast and Robust Deformable 3D Gaussian Splatting
Jiao, Han
Sun, Jiakai
Zhao, Lei
Zhang, Zhanjie
Xing, Wei
Lin, Huaizhong
Computer Vision and Pattern Recognition
Graphics
3D Gaussian Splatting has demonstrated remarkable real-time rendering capabilities and superior visual quality in novel view synthesis for static scenes. Building upon these advantages, researchers have progressively extended 3D Gaussians to dynamic scene reconstruction. Deformation field-based methods have emerged as a promising approach among various techniques. These methods maintain 3D Gaussian attributes in a canonical field and employ the deformation field to transform this field across temporal sequences. Nevertheless, these approaches frequently encounter challenges such as suboptimal rendering speeds, significant dependence on initial point clouds, and vulnerability to local optima in dim scenes. To overcome these limitations, we present FRoG, an efficient and robust framework for high-quality dynamic scene reconstruction. FRoG integrates per-Gaussian embedding with a coarse-to-fine temporal embedding strategy, accelerating rendering through the early fusion of temporal embeddings. Moreover, to enhance robustness against sparse initializations, we introduce a novel depth- and error-guided sampling strategy. This strategy populates the canonical field with new 3D Gaussians at low-deviation initial positions, significantly reducing the optimization burden on the deformation field and improving detail reconstruction in both static and dynamic regions. Furthermore, by modulating opacity variations, we mitigate the local optima problem in dim scenes, improving color fidelity. Comprehensive experimental results validate that our method achieves accelerated rendering speeds while maintaining state-of-the-art visual quality.
title Fast and Robust Deformable 3D Gaussian Splatting
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2603.20857