MV2UV: Generating High-quality UV Texture Maps with Multiview Prompts

TL;DR

MV2UV introduces a novel UV space generative model that enhances 3D texture mapping by addressing multiview inconsistency and missing textures, leveraging 2D priors and UV refinement for superior quality.

Contribution

The paper presents MV2UV, a new method combining multiview generation and UV inpainting to produce high-quality, consistent textures for 3D assets, overcoming previous limitations.

Findings

Outperforms existing methods in texture quality.

Effectively inpaints unseen parts of multiview images.

Reduces multiview inconsistency and missing textures.

Abstract

Generating high-quality textures for 3D assets is a challenging task. Existing multiview texture generation methods suffer from the multiview inconsistency and missing textures on unseen parts, while UV inpainting texture methods do not generalize well due to insufficient UV data and cannot well utilize 2D image diffusion priors. In this paper, we propose a new method called MV2UV that combines 2D generative priors from multiview generation and the inpainting ability of UV refinement to get high-quality texture maps. Our key idea is to adopt a UV space generative model that simultaneously inpaints unseen parts of multiview images while resolving the inconsistency of multiview images. Experiments show that our method enables a better texture generation quality than existing methods, especially in unseen occluded and multiview-inconsistent parts.