English

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

Computer Vision and Pattern Recognition 2024-11-25 v1 Graphics

Abstract

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.

Keywords

Cite

@article{arxiv.2411.15138,
  title  = {Material Anything: Generating Materials for Any 3D Object via Diffusion},
  author = {Xin Huang and Tengfei Wang and Ziwei Liu and Qing Wang},
  journal= {arXiv preprint arXiv:2411.15138},
  year   = {2024}
}

Comments

Project page: https://xhuangcv.github.io/MaterialAnything/

R2 v1 2026-06-28T20:09:19.787Z