UniTEX：面向三維形狀的通用高保真生成紋理技術

UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes

May 29, 2025

作者: Yixun Liang, Kunming Luo, Xiao Chen, Rui Chen, Hongyu Yan, Weiyu Li, Jiarui Liu, Ping Tan

cs.AI

摘要

我們提出了UniTEX，一種新穎的兩階段3D紋理生成框架，用於為3D資產創建高質量、一致的紋理。現有方法主要依賴於UV映射的修補技術，在將生成的多視角圖像重新投影到3D形狀上後進行紋理精修，這引入了與拓撲模糊性相關的挑戰。為解決這一問題，我們提出直接在一體化的3D功能空間中操作，從而繞過UV映射的限制。具體而言，我們首先提出通過紋理函數（TFs）將紋理生成提升至3D空間——這是一種連續的體積表示，它僅基於表面接近度將任何3D點映射到紋理值，與網格拓撲無關。接著，我們提出使用基於Transformer的大型紋理模型（LTM）直接從圖像和幾何輸入中預測這些TFs。為了進一步提升紋理質量並利用強大的2D先驗知識，我們開發了一種基於LoRA的高級策略，用於高效適應大規模擴散Transformer（DiTs），以實現高質量的多視角紋理合成，作為我們的第一階段。大量實驗表明，與現有方法相比，UniTEX在視覺質量和紋理完整性方面表現優異，為自動化3D紋理生成提供了一種可推廣且可擴展的解決方案。代碼將在以下網址提供：https://github.com/YixunLiang/UniTEX。

English

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.