MatMart: Material Reconstruction of 3D Objects via Diffusion

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wu, Xiuchao, Zhu, Pengfei, Lyu, Jiangjing, Liu, Xinguo, Guo, Jie, Guo, Yanwen, Xu, Weiwei, Lyu, Chengfei
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918216317534208
author Wu, Xiuchao
Zhu, Pengfei
Lyu, Jiangjing
Liu, Xinguo
Guo, Jie
Guo, Yanwen
Xu, Weiwei
Lyu, Chengfei
author_facet Wu, Xiuchao
Zhu, Pengfei
Lyu, Jiangjing
Liu, Xinguo
Guo, Jie
Guo, Yanwen
Xu, Weiwei
Lyu, Chengfei
contents Applying diffusion models to physically-based material estimation and generation has recently gained prominence. In this paper, we propose \ttt, a novel material reconstruction framework for 3D objects, offering the following advantages. First, \ttt\ adopts a two-stage reconstruction, starting with accurate material prediction from inputs and followed by prior-guided material generation for unobserved views, yielding high-fidelity results. Second, by utilizing progressive inference alongside the proposed view-material cross-attention (VMCA), \ttt\ enables reconstruction from an arbitrary number of input images, demonstrating strong scalability and flexibility. Finally, \ttt\ achieves both material prediction and generation capabilities through end-to-end optimization of a single diffusion model, without relying on additional pre-trained models, thereby exhibiting enhanced stability across various types of objects. Extensive experiments demonstrate that \ttt\ achieves superior performance in material reconstruction compared to existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18900
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MatMart: Material Reconstruction of 3D Objects via Diffusion
Wu, Xiuchao
Zhu, Pengfei
Lyu, Jiangjing
Liu, Xinguo
Guo, Jie
Guo, Yanwen
Xu, Weiwei
Lyu, Chengfei
Graphics
Computer Vision and Pattern Recognition
Applying diffusion models to physically-based material estimation and generation has recently gained prominence. In this paper, we propose \ttt, a novel material reconstruction framework for 3D objects, offering the following advantages. First, \ttt\ adopts a two-stage reconstruction, starting with accurate material prediction from inputs and followed by prior-guided material generation for unobserved views, yielding high-fidelity results. Second, by utilizing progressive inference alongside the proposed view-material cross-attention (VMCA), \ttt\ enables reconstruction from an arbitrary number of input images, demonstrating strong scalability and flexibility. Finally, \ttt\ achieves both material prediction and generation capabilities through end-to-end optimization of a single diffusion model, without relying on additional pre-trained models, thereby exhibiting enhanced stability across various types of objects. Extensive experiments demonstrate that \ttt\ achieves superior performance in material reconstruction compared to existing methods.
title MatMart: Material Reconstruction of 3D Objects via Diffusion
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.18900