DualMat: PBR Material Estimation via Coherent Dual-Path Diffusion
By: Yifeng Huang , Zhang Chen , Yi Xu and more
Potential Business Impact:
Makes pictures look real with better light and texture.
We present DualMat, a novel dual-path diffusion framework for estimating Physically Based Rendering (PBR) materials from single images under complex lighting conditions. Our approach operates in two distinct latent spaces: an albedo-optimized path leveraging pretrained visual knowledge through RGB latent space, and a material-specialized path operating in a compact latent space designed for precise metallic and roughness estimation. To ensure coherent predictions between the albedo-optimized and material-specialized paths, we introduce feature distillation during training. We employ rectified flow to enhance efficiency by reducing inference steps while maintaining quality. Our framework extends to high-resolution and multi-view inputs through patch-based estimation and cross-view attention, enabling seamless integration into image-to-3D pipelines. DualMat achieves state-of-the-art performance on both Objaverse and real-world data, significantly outperforming existing methods with up to 28% improvement in albedo estimation and 39% reduction in metallic-roughness prediction errors.
Similar Papers
MatLat: Material Latent Space for PBR Texture Generation
CV and Pattern Recognition
Makes 3D objects look real with better textures.
MatPedia: A Universal Generative Foundation for High-Fidelity Material Synthesis
CV and Pattern Recognition
Creates realistic computer images from simple descriptions.
MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion
CV and Pattern Recognition
Makes 3D objects look real in any light.