UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes

TL;DR

UniTEX introduces a 3D texture generation framework that operates directly in a unified 3D space, bypassing UV mapping limitations, and uses transformer-based models to produce high-quality, consistent textures for 3D shapes.

Contribution

It proposes a novel 3D functional space for texture generation and a transformer-based model with efficient adaptation strategies, advancing 3D texture synthesis beyond UV-based methods.

Findings

Achieves superior visual quality over existing methods.

Provides a scalable, generalizable solution for 3D texture generation.

Demonstrates effective multi-view texture synthesis with high fidelity.

Abstract

We present UniTEX, a novel two-stage 3D texture generation framework to create high-quality, consistent textures for 3D assets. Existing approaches predominantly rely on UV-based inpainting to refine textures after reprojecting the generated multi-view images onto the 3D shapes, which introduces challenges related to topological ambiguity. To address this, we propose to bypass the limitations of UV mapping by operating directly in a unified 3D functional space. Specifically, we first propose that lifts texture generation into 3D space via Texture Functions (TFs)--a continuous, volumetric representation that maps any 3D point to a texture value based solely on surface proximity, independent of mesh topology. Then, we propose to predict these TFs directly from images and geometry inputs using a transformer-based Large Texturing Model (LTM). To further enhance texture quality and leverage powerful 2D priors, we develop an advanced LoRA-based strategy for efficiently adapting large-scale Diffusion Transformers (DiTs) for high-quality multi-view texture synthesis as our first stage. Extensive experiments demonstrate that UniTEX achieves superior visual quality and texture integrity compared to existing approaches, offering a generalizable and scalable solution for automated 3D texture generation. Code will available in: https://github.com/YixunLiang/UniTEX.