MatPedia: A Universal Generative Foundation for High-Fidelity Material Synthesis

TL;DR

MatPedia introduces a unified foundation model for high-fidelity material synthesis that bridges natural image appearance and PBR properties, enabling versatile material generation tasks with superior quality.

Contribution

It proposes a novel joint RGB-PBR representation and a unified framework that leverages large-scale RGB data for diverse material synthesis tasks.

Findings

Achieves native 1024x1024 material synthesis surpassing existing methods.

Enables multiple material tasks within a single architecture.

Leverages large-scale RGB data for improved material generation quality.

Abstract

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.