DeMapGS: Simultaneous Mesh Deformation and Surface Attribute Mapping via Gaussian Splatting

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhou, Shuyi, Zhong, Shengze, Takayama, Kenshi, Taketomi, Takafumi, Oishi, Takeshi
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917138684444672
author Zhou, Shuyi
Zhong, Shengze
Takayama, Kenshi
Taketomi, Takafumi
Oishi, Takeshi
author_facet Zhou, Shuyi
Zhong, Shengze
Takayama, Kenshi
Taketomi, Takafumi
Oishi, Takeshi
contents We propose DeMapGS, a structured Gaussian Splatting framework that jointly optimizes deformable surfaces and surface-attached 2D Gaussian splats. By anchoring splats to a deformable template mesh, our method overcomes topological inconsistencies and enhances editing flexibility, addressing limitations of prior Gaussian Splatting methods that treat points independently. The unified representation in our method supports extraction of high-fidelity diffuse, normal, and displacement maps, enabling the reconstructed mesh to inherit the photorealistic rendering quality of Gaussian Splatting. To support robust optimization, we introduce a gradient diffusion strategy that propagates supervision across the surface, along with an alternating 2D/3D rendering scheme to handle concave regions. Experiments demonstrate that DeMapGS achieves state-of-the-art mesh reconstruction quality and enables downstream applications for Gaussian splats such as editing and cross-object manipulation through a shared parametric surface.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10572
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DeMapGS: Simultaneous Mesh Deformation and Surface Attribute Mapping via Gaussian Splatting
Zhou, Shuyi
Zhong, Shengze
Takayama, Kenshi
Taketomi, Takafumi
Oishi, Takeshi
Graphics
We propose DeMapGS, a structured Gaussian Splatting framework that jointly optimizes deformable surfaces and surface-attached 2D Gaussian splats. By anchoring splats to a deformable template mesh, our method overcomes topological inconsistencies and enhances editing flexibility, addressing limitations of prior Gaussian Splatting methods that treat points independently. The unified representation in our method supports extraction of high-fidelity diffuse, normal, and displacement maps, enabling the reconstructed mesh to inherit the photorealistic rendering quality of Gaussian Splatting. To support robust optimization, we introduce a gradient diffusion strategy that propagates supervision across the surface, along with an alternating 2D/3D rendering scheme to handle concave regions. Experiments demonstrate that DeMapGS achieves state-of-the-art mesh reconstruction quality and enables downstream applications for Gaussian splats such as editing and cross-object manipulation through a shared parametric surface.
title DeMapGS: Simultaneous Mesh Deformation and Surface Attribute Mapping via Gaussian Splatting
topic Graphics
url https://arxiv.org/abs/2512.10572