Saved in:
Bibliographic Details
Main Authors: Wang, Xuyang, Cheng, Ziang, Li, Zhenyu, Yang, Jiayu, Ji, Haorui, Ji, Pan, Harandi, Mehrtash, Hartley, Richard, Li, Hongdong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.03397
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910900728889344
author Wang, Xuyang
Cheng, Ziang
Li, Zhenyu
Yang, Jiayu
Ji, Haorui
Ji, Pan
Harandi, Mehrtash
Hartley, Richard
Li, Hongdong
author_facet Wang, Xuyang
Cheng, Ziang
Li, Zhenyu
Yang, Jiayu
Ji, Haorui
Ji, Pan
Harandi, Mehrtash
Hartley, Richard
Li, Hongdong
contents This paper addresses the problem of generating textures for 3D mesh assets. Existing approaches often rely on image diffusion models to generate multi-view image observations, which are then transformed onto the mesh surface to produce a single texture. However, due to the gap between multi-view images and 3D space, such process is susceptible to arange of issues such as geometric inconsistencies, visibility occlusion, and baking artifacts. To overcome this problem, we propose a novel approach that directly generates texture on 3D meshes. Our approach leverages heat dissipation diffusion, which serves as an efficient operator that propagates features on the geometric surface of a mesh, while remaining insensitive to the specific layout of the wireframe. By integrating this technique into a generative diffusion pipeline, we significantly improve the efficiency of texture generation compared to existing texture generation methods. We term our approach DoubleDiffusion, as it combines heat dissipation diffusion with denoising diffusion to enable native generative learning on 3D mesh surfaces.
format Preprint
id arxiv_https___arxiv_org_abs_2501_03397
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DoubleDiffusion: Combining Heat Diffusion with Denoising Diffusion for Texture Generation on 3D Meshes
Wang, Xuyang
Cheng, Ziang
Li, Zhenyu
Yang, Jiayu
Ji, Haorui
Ji, Pan
Harandi, Mehrtash
Hartley, Richard
Li, Hongdong
Computer Vision and Pattern Recognition
This paper addresses the problem of generating textures for 3D mesh assets. Existing approaches often rely on image diffusion models to generate multi-view image observations, which are then transformed onto the mesh surface to produce a single texture. However, due to the gap between multi-view images and 3D space, such process is susceptible to arange of issues such as geometric inconsistencies, visibility occlusion, and baking artifacts. To overcome this problem, we propose a novel approach that directly generates texture on 3D meshes. Our approach leverages heat dissipation diffusion, which serves as an efficient operator that propagates features on the geometric surface of a mesh, while remaining insensitive to the specific layout of the wireframe. By integrating this technique into a generative diffusion pipeline, we significantly improve the efficiency of texture generation compared to existing texture generation methods. We term our approach DoubleDiffusion, as it combines heat dissipation diffusion with denoising diffusion to enable native generative learning on 3D mesh surfaces.
title DoubleDiffusion: Combining Heat Diffusion with Denoising Diffusion for Texture Generation on 3D Meshes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.03397