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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xiang, Xiaoyu, Gorelik, Liat Sless, Fan, Yuchen, Armstrong, Omri, Iandola, Forrest, Li, Yilei, Lifshitz, Ita, Ranjan, Rakesh
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916583696236544
author Xiang, Xiaoyu
Gorelik, Liat Sless
Fan, Yuchen
Armstrong, Omri
Iandola, Forrest
Li, Yilei
Lifshitz, Ita
Ranjan, Rakesh
author_facet Xiang, Xiaoyu
Gorelik, Liat Sless
Fan, Yuchen
Armstrong, Omri
Iandola, Forrest
Li, Yilei
Lifshitz, Ita
Ranjan, Rakesh
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_07766
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Make-A-Texture: Fast Shape-Aware Texture Generation in 3 Seconds
Xiang, Xiaoyu
Gorelik, Liat Sless
Fan, Yuchen
Armstrong, Omri
Iandola, Forrest
Li, Yilei
Lifshitz, Ita
Ranjan, Rakesh
Computer Vision and Pattern Recognition
Graphics
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.
title Make-A-Texture: Fast Shape-Aware Texture Generation in 3 Seconds
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2412.07766