TexPainter: Generative Mesh Texturing with Multi-view Consistency

TL;DR

TexPainter introduces a novel optimization-based approach to generate multi-view consistent textures for 3D meshes using pre-trained diffusion models, improving quality and consistency over previous methods.

Contribution

The paper proposes a new method that enforces multi-view consistency in texture generation by gradient-based optimization, relaxing sequential view dependencies in diffusion models.

Findings

Improves multi-view consistency of generated textures

Enhances overall texture quality compared to state-of-the-art methods

Demonstrates effectiveness on various 3D models

Abstract

The recent success of pre-trained diffusion models unlocks the possibility of the automatic generation of textures for arbitrary 3D meshes in the wild. However, these models are trained in the screen space, while converting them to a multi-view consistent texture image poses a major obstacle to the output quality. In this paper, we propose a novel method to enforce multi-view consistency. Our method is based on the observation that latent space in a pre-trained diffusion model is noised separately for each camera view, making it difficult to achieve multi-view consistency by directly manipulating the latent codes. Based on the celebrated Denoising Diffusion Implicit Models (DDIM) scheme, we propose to use an optimization-based color-fusion to enforce consistency and indirectly modify the latent codes by gradient back-propagation. Our method further relaxes the sequential dependency assumption among the camera views. By evaluating on a series of general 3D models, we find our simple approach improves consistency and overall quality of the generated textures as compared to competing state-of-the-arts. Our implementation is available at: https://github.com/Quantuman134/TexPainter