English

MatFormer: A Generative Model for Procedural Materials

Graphics 2022-08-16 v2

Abstract

Procedural material graphs are a compact, parameteric, and resolution-independent representation that are a popular choice for material authoring. However, designing procedural materials requires significant expertise and publicly accessible libraries contain only a few thousand such graphs. We present MatFormer, a generative model that can produce a diverse set of high-quality procedural materials with complex spatial patterns and appearance. While procedural materials can be modeled as directed (operation) graphs, they contain arbitrary numbers of heterogeneous nodes with unstructured, often long-range node connections, and functional constraints on node parameters and connections. MatFormer addresses these challenges with a multi-stage transformer-based model that sequentially generates nodes, node parameters, and edges, while ensuring the semantic validity of the graph. In addition to generation, MatFormer can be used for the auto-completion and exploration of partial material graphs. We qualitatively and quantitatively demonstrate that our method outperforms alternative approaches, in both generated graph and material quality.

Keywords

Cite

@article{arxiv.2207.01044,
  title  = {MatFormer: A Generative Model for Procedural Materials},
  author = {Paul Guerrero and Miloš Hašan and Kalyan Sunkavalli and Radomír Měch and Tamy Boubekeur and Niloy J. Mitra},
  journal= {arXiv preprint arXiv:2207.01044},
  year   = {2022}
}
R2 v1 2026-06-24T12:12:27.307Z