SuperMat: Physically Consistent PBR Material Estimation at Interactive Rates

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hong, Yijia, Guo, Yuan-Chen, Yi, Ran, Chen, Yulong, Cao, Yan-Pei, Ma, Lizhuang
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909935412969472
author Hong, Yijia
Guo, Yuan-Chen
Yi, Ran
Chen, Yulong
Cao, Yan-Pei
Ma, Lizhuang
author_facet Hong, Yijia
Guo, Yuan-Chen
Yi, Ran
Chen, Yulong
Cao, Yan-Pei
Ma, Lizhuang
contents Decomposing physically-based materials from images into their constituent properties remains challenging, particularly when maintaining both computational efficiency and physical consistency. While recent diffusion-based approaches have shown promise, they face substantial computational overhead due to multiple denoising steps and separate models for different material properties. We present SuperMat, a single-step framework that achieves high-quality material decomposition with one-step inference. This enables end-to-end training with perceptual and re-render losses while decomposing albedo, metallic, and roughness maps at millisecond-scale speeds. We further extend our framework to 3D objects through a UV refinement network, enabling consistent material estimation across viewpoints while maintaining efficiency. Experiments demonstrate that SuperMat achieves state-of-the-art PBR material decomposition quality while reducing inference time from seconds to milliseconds per image, and completes PBR material estimation for 3D objects in approximately 3 seconds. The project page is at https://hyj542682306.github.io/SuperMat/.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17515
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SuperMat: Physically Consistent PBR Material Estimation at Interactive Rates
Hong, Yijia
Guo, Yuan-Chen
Yi, Ran
Chen, Yulong
Cao, Yan-Pei
Ma, Lizhuang
Computer Vision and Pattern Recognition
Decomposing physically-based materials from images into their constituent properties remains challenging, particularly when maintaining both computational efficiency and physical consistency. While recent diffusion-based approaches have shown promise, they face substantial computational overhead due to multiple denoising steps and separate models for different material properties. We present SuperMat, a single-step framework that achieves high-quality material decomposition with one-step inference. This enables end-to-end training with perceptual and re-render losses while decomposing albedo, metallic, and roughness maps at millisecond-scale speeds. We further extend our framework to 3D objects through a UV refinement network, enabling consistent material estimation across viewpoints while maintaining efficiency. Experiments demonstrate that SuperMat achieves state-of-the-art PBR material decomposition quality while reducing inference time from seconds to milliseconds per image, and completes PBR material estimation for 3D objects in approximately 3 seconds. The project page is at https://hyj542682306.github.io/SuperMat/.
title SuperMat: Physically Consistent PBR Material Estimation at Interactive Rates
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.17515