MV2UV: Generating High-quality UV Texture Maps with Multiview Prompts
This work solves the challenge of creating consistent and complete textures for 3D models, which is incremental as it builds on existing multiview and UV inpainting methods.
The paper tackled the problem of generating high-quality textures for 3D assets by addressing multiview inconsistency and missing textures in unseen parts, resulting in improved texture generation quality, especially for occluded and inconsistent areas.
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.