MatPedia: A Universal Generative Foundation for High-Fidelity Material Synthesis
This addresses the challenge of fragmented and inefficient material creation for photorealistic graphics, offering a unified solution for researchers and practitioners in computer graphics and AI.
The paper tackles the problem of labor-intensive creation of physically-based rendering (PBR) materials by introducing MatPedia, a foundation model that uses a joint RGB-PBR representation to unify material synthesis tasks, achieving high-fidelity synthesis at 1024x1024 resolution that surpasses existing methods in quality and diversity.
Physically-based rendering (PBR) materials are fundamental to photorealistic graphics, yet their creation remains labor-intensive and requires specialized expertise. While generative models have advanced material synthesis, existing methods lack a unified representation bridging natural image appearance and PBR properties, leading to fragmented task-specific pipelines and inability to leverage large-scale RGB image data. We present MatPedia, a foundation model built upon a novel joint RGB-PBR representation that compactly encodes materials into two interdependent latents: one for RGB appearance and one for the four PBR maps encoding complementary physical properties. By formulating them as a 5-frame sequence and employing video diffusion architectures, MatPedia naturally captures their correlations while transferring visual priors from RGB generation models. This joint representation enables a unified framework handling multiple material tasks--text-to-material generation, image-to-material generation, and intrinsic decomposition--within a single architecture. Trained on MatHybrid-410K, a mixed corpus combining PBR datasets with large-scale RGB images, MatPedia achieves native $1024\times1024$ synthesis that substantially surpasses existing approaches in both quality and diversity.