Material Anything: Generating Materials for Any 3D Object via Diffusion

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Huang, Xin, Wang, Tengfei, Liu, Ziwei, Wang, Qing
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929601149665280
author Huang, Xin
Wang, Tengfei
Liu, Ziwei
Wang, Qing
author_facet Huang, Xin
Wang, Tengfei
Liu, Ziwei
Wang, Qing
contents We present Material Anything, a fully-automated, unified diffusion framework designed to generate physically-based materials for 3D objects. Unlike existing methods that rely on complex pipelines or case-specific optimizations, Material Anything offers a robust, end-to-end solution adaptable to objects under diverse lighting conditions. Our approach leverages a pre-trained image diffusion model, enhanced with a triple-head architecture and rendering loss to improve stability and material quality. Additionally, we introduce confidence masks as a dynamic switcher within the diffusion model, enabling it to effectively handle both textured and texture-less objects across varying lighting conditions. By employing a progressive material generation strategy guided by these confidence masks, along with a UV-space material refiner, our method ensures consistent, UV-ready material outputs. Extensive experiments demonstrate our approach outperforms existing methods across a wide range of object categories and lighting conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2411_15138
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Material Anything: Generating Materials for Any 3D Object via Diffusion
Huang, Xin
Wang, Tengfei
Liu, Ziwei
Wang, Qing
Computer Vision and Pattern Recognition
Graphics
We present Material Anything, a fully-automated, unified diffusion framework designed to generate physically-based materials for 3D objects. Unlike existing methods that rely on complex pipelines or case-specific optimizations, Material Anything offers a robust, end-to-end solution adaptable to objects under diverse lighting conditions. Our approach leverages a pre-trained image diffusion model, enhanced with a triple-head architecture and rendering loss to improve stability and material quality. Additionally, we introduce confidence masks as a dynamic switcher within the diffusion model, enabling it to effectively handle both textured and texture-less objects across varying lighting conditions. By employing a progressive material generation strategy guided by these confidence masks, along with a UV-space material refiner, our method ensures consistent, UV-ready material outputs. Extensive experiments demonstrate our approach outperforms existing methods across a wide range of object categories and lighting conditions.
title Material Anything: Generating Materials for Any 3D Object via Diffusion
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2411.15138