DynaSplat: Dynamic-Static Gaussian Splatting with Hierarchical Motion Decomposition for Scene Reconstruction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Deng, Junli, Shi, Ping, Li, Qipei, Guo, Jinyang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912425109880832
author Deng, Junli
Shi, Ping
Li, Qipei
Guo, Jinyang
author_facet Deng, Junli
Shi, Ping
Li, Qipei
Guo, Jinyang
contents Reconstructing intricate, ever-changing environments remains a central ambition in computer vision, yet existing solutions often crumble before the complexity of real-world dynamics. We present DynaSplat, an approach that extends Gaussian Splatting to dynamic scenes by integrating dynamic-static separation and hierarchical motion modeling. First, we classify scene elements as static or dynamic through a novel fusion of deformation offset statistics and 2D motion flow consistency, refining our spatial representation to focus precisely where motion matters. We then introduce a hierarchical motion modeling strategy that captures both coarse global transformations and fine-grained local movements, enabling accurate handling of intricate, non-rigid motions. Finally, we integrate physically-based opacity estimation to ensure visually coherent reconstructions, even under challenging occlusions and perspective shifts. Extensive experiments on challenging datasets reveal that DynaSplat not only surpasses state-of-the-art alternatives in accuracy and realism but also provides a more intuitive, compact, and efficient route to dynamic scene reconstruction.
format Preprint
id arxiv_https___arxiv_org_abs_2506_09836
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DynaSplat: Dynamic-Static Gaussian Splatting with Hierarchical Motion Decomposition for Scene Reconstruction
Deng, Junli
Shi, Ping
Li, Qipei
Guo, Jinyang
Computer Vision and Pattern Recognition
Artificial Intelligence
Reconstructing intricate, ever-changing environments remains a central ambition in computer vision, yet existing solutions often crumble before the complexity of real-world dynamics. We present DynaSplat, an approach that extends Gaussian Splatting to dynamic scenes by integrating dynamic-static separation and hierarchical motion modeling. First, we classify scene elements as static or dynamic through a novel fusion of deformation offset statistics and 2D motion flow consistency, refining our spatial representation to focus precisely where motion matters. We then introduce a hierarchical motion modeling strategy that captures both coarse global transformations and fine-grained local movements, enabling accurate handling of intricate, non-rigid motions. Finally, we integrate physically-based opacity estimation to ensure visually coherent reconstructions, even under challenging occlusions and perspective shifts. Extensive experiments on challenging datasets reveal that DynaSplat not only surpasses state-of-the-art alternatives in accuracy and realism but also provides a more intuitive, compact, and efficient route to dynamic scene reconstruction.
title DynaSplat: Dynamic-Static Gaussian Splatting with Hierarchical Motion Decomposition for Scene Reconstruction
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2506.09836