TEXGen: a Generative Diffusion Model for Mesh Textures
This addresses the need for realistic 3D rendering textures, offering a novel approach that is not incremental but introduces a new method for a known bottleneck in texture generation.
The authors tackled the problem of generating high-quality texture maps for 3D assets by training a large diffusion model that directly generates high-resolution UV texture maps in a feed-forward manner, achieving this with a 700 million parameter model that supports text and image guidance.
While high-quality texture maps are essential for realistic 3D asset rendering, few studies have explored learning directly in the texture space, especially on large-scale datasets. In this work, we depart from the conventional approach of relying on pre-trained 2D diffusion models for test-time optimization of 3D textures. Instead, we focus on the fundamental problem of learning in the UV texture space itself. For the first time, we train a large diffusion model capable of directly generating high-resolution texture maps in a feed-forward manner. To facilitate efficient learning in high-resolution UV spaces, we propose a scalable network architecture that interleaves convolutions on UV maps with attention layers on point clouds. Leveraging this architectural design, we train a 700 million parameter diffusion model that can generate UV texture maps guided by text prompts and single-view images. Once trained, our model naturally supports various extended applications, including text-guided texture inpainting, sparse-view texture completion, and text-driven texture synthesis. Project page is at http://cvmi-lab.github.io/TEXGen/.