Generating Surface for Text-to-3D using 2D Gaussian Splatting

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Dong, Huanning, Li, Fan, Kuang, Ping, Min, Jianwen
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908581853396992
author Dong, Huanning
Li, Fan
Kuang, Ping
Min, Jianwen
author_facet Dong, Huanning
Li, Fan
Kuang, Ping
Min, Jianwen
contents Recent advancements in Text-to-3D modeling have shown significant potential for the creation of 3D content. However, due to the complex geometric shapes of objects in the natural world, generating 3D content remains a challenging task. Current methods either leverage 2D diffusion priors to recover 3D geometry, or train the model directly based on specific 3D representations. In this paper, we propose a novel method named DirectGaussian, which focuses on generating the surfaces of 3D objects represented by surfels. In DirectGaussian, we utilize conditional text generation models and the surface of a 3D object is rendered by 2D Gaussian splatting with multi-view normal and texture priors. For multi-view geometric consistency problems, DirectGaussian incorporates curvature constraints on the generated surface during optimization process. Through extensive experiments, we demonstrate that our framework is capable of achieving diverse and high-fidelity 3D content creation.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06967
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generating Surface for Text-to-3D using 2D Gaussian Splatting
Dong, Huanning
Li, Fan
Kuang, Ping
Min, Jianwen
Computer Vision and Pattern Recognition
Artificial Intelligence
Recent advancements in Text-to-3D modeling have shown significant potential for the creation of 3D content. However, due to the complex geometric shapes of objects in the natural world, generating 3D content remains a challenging task. Current methods either leverage 2D diffusion priors to recover 3D geometry, or train the model directly based on specific 3D representations. In this paper, we propose a novel method named DirectGaussian, which focuses on generating the surfaces of 3D objects represented by surfels. In DirectGaussian, we utilize conditional text generation models and the surface of a 3D object is rendered by 2D Gaussian splatting with multi-view normal and texture priors. For multi-view geometric consistency problems, DirectGaussian incorporates curvature constraints on the generated surface during optimization process. Through extensive experiments, we demonstrate that our framework is capable of achieving diverse and high-fidelity 3D content creation.
title Generating Surface for Text-to-3D using 2D Gaussian Splatting
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2510.06967