We present Make-A-Texture, a new framework that efficiently synthesizes high-resolution texture maps from textual prompts for given 3D geometries. Our approach progressively generates textures that are consistent across multiple viewpoints with a depth-aware inpainting diffusion model, in an optimized sequence of viewpoints determined by an automatic view selection algorithm. A significant feature of our method is its remarkable efficiency, achieving a full texture generation within an end-to-end runtime of just 3.07 seconds on a single NVIDIA H100 GPU, significantly outperforming existing methods. Such an acceleration is achieved by optimizations in the diffusion model and a specialized backprojection method. Moreover, our method reduces the artifacts in the backprojection phase, by selectively masking out non-frontal faces, and internal faces of open-surfaced objects. Experimental results demonstrate that Make-A-Texture matches or exceeds the quality of other state-of-the-art methods. Our work significantly improves the applicability and practicality of texture generation models for real-world 3D content creation, including interactive creation and text-guided texture editing.
@article{arxiv.2412.07766,
title = {Make-A-Texture: Fast Shape-Aware Texture Generation in 3 Seconds},
author = {Xiaoyu Xiang and Liat Sless Gorelik and Yuchen Fan and Omri Armstrong and Forrest Iandola and Yilei Li and Ita Lifshitz and Rakesh Ranjan},
journal= {arXiv preprint arXiv:2412.07766},
year = {2025}
}
Comments
Accepted to WACV 2025 Webpage: https://mukosame.github.io/make-a-texture/ Video: https://www.youtube.com/watch?v=2Ctqdx1uaj0