{"ID":2885023,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.05060","arxiv_id":"2508.05060","title":"DualMat: PBR Material Estimation via Coherent Dual-Path Diffusion","abstract":"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.","short_abstract":"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 m...","url_abs":"https://arxiv.org/abs/2508.05060","url_pdf":"https://arxiv.org/pdf/2508.05060v1","authors":"[\"Yifeng Huang\",\"Zhang Chen\",\"Yi Xu\",\"Minh Hoai\",\"Zhong Li\"]","published":"2025-08-07T06:25:45Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}