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

TL;DR

Make-A-Texture is a highly efficient framework that generates high-resolution, shape-aware textures from text prompts in just over 3 seconds, enabling real-time 3D content creation.

Contribution

It introduces a fast, optimized diffusion-based method with view selection and backprojection improvements for rapid, high-quality texture synthesis from text prompts.

Findings

Texture generation completed in 3.07 seconds on a single GPU

Achieves comparable or better quality than state-of-the-art methods

Enables real-time, interactive 3D texture editing

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.