學習具有一般化紋理UV輻射場

TUVF: Learning Generalizable Texture UV Radiance Fields

May 4, 2023

作者: An-Chieh Cheng, Xueting Li, Sifei Liu, Xiaolong Wang

cs.AI

摘要

紋理是創建視覺上吸引人且逼真的3D模型的重要方面。本文研究生成高保真度紋理的問題，這相對於通用3D形狀建模來說，探索較少。我們的目標是促進可控制的紋理生成過程，使一個紋理編碼能夠對應到特定外觀風格，獨立於來自某一類別的任何輸入形狀。我們引入紋理UV輻射場（TUVF），在可學習的UV球空間中生成紋理，而非直接在3D形狀上。這使得紋理能夠從底層形狀中解開並可轉移到共享相同UV空間的其他形狀，即來自同一類別。我們將UV球空間與輻射場結合，提供比傳統紋理貼圖更高效和準確的紋理表示。我們在真實物件數據集上進行實驗，不僅實現了逼真的合成，還在紋理控制和編輯方面顯著優於最先進技術。項目頁面：https://www.anjiecheng.me/TUVF

English

Textures are a vital aspect of creating visually appealing and realistic 3D models. In this paper, we study the problem of generating high-fidelity texture given shapes of 3D assets, which has been relatively less explored compared with generic 3D shape modeling. Our goal is to facilitate a controllable texture generation process, such that one texture code can correspond to a particular appearance style independent of any input shapes from a category. We introduce Texture UV Radiance Fields (TUVF) that generate textures in a learnable UV sphere space rather than directly on the 3D shape. This allows the texture to be disentangled from the underlying shape and transferable to other shapes that share the same UV space, i.e., from the same category. We integrate the UV sphere space with the radiance field, which provides a more efficient and accurate representation of textures than traditional texture maps. We perform our experiments on real-world object datasets where we achieve not only realistic synthesis but also substantial improvements over state-of-the-arts on texture controlling and editing. Project Page: https://www.anjiecheng.me/TUVF