CVAIGRAug 21, 2023

Texture Generation on 3D Meshes with Point-UV Diffusion

arXiv:2308.10490v178 citationsh-index: 58Has Code
Originality Incremental advance
AI Analysis

This addresses the challenge of texture generation for 3D models, which is incremental as it builds on diffusion models and UV mapping.

The paper tackles the problem of synthesizing high-quality textures on 3D meshes by proposing Point-UV diffusion, a coarse-to-fine pipeline that generates 3D consistent and high-fidelity texture images in UV space, capable of processing meshes of any genus.

In this work, we focus on synthesizing high-quality textures on 3D meshes. We present Point-UV diffusion, a coarse-to-fine pipeline that marries the denoising diffusion model with UV mapping to generate 3D consistent and high-quality texture images in UV space. We start with introducing a point diffusion model to synthesize low-frequency texture components with our tailored style guidance to tackle the biased color distribution. The derived coarse texture offers global consistency and serves as a condition for the subsequent UV diffusion stage, aiding in regularizing the model to generate a 3D consistent UV texture image. Then, a UV diffusion model with hybrid conditions is developed to enhance the texture fidelity in the 2D UV space. Our method can process meshes of any genus, generating diversified, geometry-compatible, and high-fidelity textures. Code is available at https://cvmi-lab.github.io/Point-UV-Diffusion

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes