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.
@article{arxiv.2511.18900,
title = {MatMart: Material Reconstruction of 3D Objects via Diffusion},
author = {Xiuchao Wu and Pengfei Zhu and Jiangjing Lyu and Xinguo Liu and Jie Guo and Yanwen Guo and Weiwei Xu and Chengfei Lyu},
journal= {arXiv preprint arXiv:2511.18900},
year = {2025}
}