TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models

TL;DR

TexFusion is a novel method that uses large-scale text-guided image diffusion models to efficiently generate high-quality, globally coherent textures for 3D objects without relying on ground truth textures or slow optimization.

Contribution

It introduces a 3D-consistent texture synthesis technique leveraging diffusion models on multiple views, outperforming prior distillation-based methods in quality and efficiency.

Findings

Achieves state-of-the-art text-guided texture synthesis performance.

Generates diverse, high-quality, and globally coherent textures.

Does not require ground truth 3D textures for training.

Abstract

We present TexFusion (Texture Diffusion), a new method to synthesize textures for given 3D geometries, using large-scale text-guided image diffusion models. In contrast to recent works that leverage 2D text-to-image diffusion models to distill 3D objects using a slow and fragile optimization process, TexFusion introduces a new 3D-consistent generation technique specifically designed for texture synthesis that employs regular diffusion model sampling on different 2D rendered views. Specifically, we leverage latent diffusion models, apply the diffusion model's denoiser on a set of 2D renders of the 3D object, and aggregate the different denoising predictions on a shared latent texture map. Final output RGB textures are produced by optimizing an intermediate neural color field on the decodings of 2D renders of the latent texture. We thoroughly validate TexFusion and show that we can efficiently generate diverse, high quality and globally coherent textures. We achieve state-of-the-art text-guided texture synthesis performance using only image diffusion models, while avoiding the pitfalls of previous distillation-based methods. The text-conditioning offers detailed control and we also do not rely on any ground truth 3D textures for training. This makes our method versatile and applicable to a broad range of geometry and texture types. We hope that TexFusion will advance AI-based texturing of 3D assets for applications in virtual reality, game design, simulation, and more.