UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes

TL;DR

UniTEX tackles 3D texture generation by removing reliance on UV parameterizations and topological ambiguity. It introduces Texture Functions, a continuous 3D texture representation regressed by a Large Texturing Model from multi-view images and geometry, with a LoRA-augmented diffusion-tensor for efficient multi-view synthesis. The two-stage pipeline demonstrates superior texture quality and consistency across artist-created and generative meshes, supported by extensive qualitative and quantitative evaluations and ablations. This approach enables scalable, UV-free texturing that leverages powerful 2D priors while providing complete 3D texture fields. Code will be available at the project repository.

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.

Figures (9)

• Figure 1: UniTEX generates high-quality and complete textures for both artist-created low-polygon mesh (the van shell) and generative high-polygon meshes (robots, toy bear, bust and roadsign).
• Figure 2: UV-based texturing models perform well on in-domain, artist-created meshes (first column), but struggle with out-of-distribution, generated meshes (second column). We take Paint3D zeng2024paint3d and TexGEN yu2024texgen as representative examples: while effective on large, continuous regions, they fail to handle small, fragmented areas due to training biases toward clean, large-region UV layouts. In contrast, our method operates outside the UV space, enabling better generalization across diverse mesh types. Additional comparisons are provided in Sec. \ref{['sec:refinement_stage_comp']}.
• Figure 3: Overall pipeline of UniTEX. Given a textureless geometry and reference image, UniTEX first generates a high-fidelity multi-view image through 3 steps (RGB generation, delighting, and super-resolution (SR)) using finetuned DiTs (detailed in Sec. \ref{['sec:imporve_training']}). The texture will be reprojected to a partial textured mesh and sent to the Large Texturing Model (Detailed in Sec. \ref{['sec:ltm']}) with generated images to predict the corresponding complete texture functions (Detailed in Sec. \ref{['sec:training_obj']}). The final texture is then synthesized by blending the predicted texture functions with the partial textured geometry.
• Figure 4: Pipeline of the Large Texturing Model. Given a partially textured geometry and six input views, we first unify them into a shared triplane-cube token representation. A transformer-based architecture then processes these tokens to extract geometry-aware features, which are subsequently decoded into colors using a lightweight MLP.
• Figure 5: Visualized example of the Texture Functions (TF) for represent the texture for the whole 3D space. (a) A textured mesh. (b) Unsigned Distance Function (UDF) samples representing 3D geometry. (c) Inspired by UDF, we define texture as a continuous function over 3D space (details in Sec. \ref{['sec:training_obj']}), enabling volumetric texture representation.