Make-A-Texture: Fast Shape-Aware Texture Generation in 3 Seconds

Xiaoyu Xiang, Liat Sless Gorelik, Yuchen Fan, Omri Armstrong, Forrest Iandola, Yilei Li, Ita Lifshitz, Rakesh Ranjan
Meta
WACV 2025
Paper Poster Video arXiv
Teaser Image

Given a textureless 3D mesh and a text prompt, Make-A-Texture efficiently synthesizes high-quality textures with 3 seconds.

Abstract

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.

Architecture

Pipeline

Method overview. The texture is generated iteratively from different viewpoints using a pretrained diffusion model. At the 1st stage, we generate the front and back view together for better global consistency. In following stages, the output RGB is conditioned on both geometry and the existing textures via inpainting. The generated images are backprojected to the mesh surface to for the next stage.

Visual Comparison

Comparison

Qualitative comparison with previous works.

Visualization of Textured Outputs

-->

Video Presentation

BibTeX

@inproceedings{xiang2025makeatexture,
        title={Make-A-Texture: Fast Shape-Aware Texture Generation in 3 Seconds},
        author={Xiaoyu Xiang, Liat Sless Gorelik, Yuchen Fan, Omri Armstrong, Forrest Iandola, Yilei Li, Ita Lifshitz, Rakesh Ranjan},
        booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
        year={2025}
      }