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

Source: [MatPedia: A Universal Generative Foundation for High-Fidelity Material Synthesis](<https://www.sota2.com/research/paper/6923e6aed6b0dd334292f19b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-06T05:00:05.533Z

Authors: Di Luo, Shuhui Yang, Mingxin Yang, Jiawei Lu, Yixuan Tang, Xintong Han, Zhuo Chen, Beibei Wang, Chunchao Guo

Published: 2025-11-21T05:16:26.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image-to-Material Generation on Single Real-world Images](<https://www.sota2.com/research/sota/image-to-material-generation-on-single-real-world-images.md>): Image-to-Material Generation; Single real-world images; CLIP Score (Basecolor): 0.943.

- [Material Decomposition on Material Decomposition Dataset](<https://www.sota2.com/research/sota/material-decomposition-on-material-decomposition-dataset.md>): Material Decomposition; Material Decomposition Dataset; MSE (basecolor): 0.009.

- [Text-to-material generation on MaterialPicker (test)](<https://www.sota2.com/research/sota/text-to-material-generation-on-materialpicker-test.md>): Text-to-material generation; MaterialPicker (test); CLIP Score: 28.3.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2511.16957>)

[PDF](<https://arxiv.org/pdf/2511.16957.pdf>)
