MatFormer: A Generative Model for Procedural Materials

TL;DR

MatFormer is a transformer-based generative model that creates diverse, high-quality procedural material graphs with complex patterns, enabling easier material authoring and exploration.

Contribution

We introduce MatFormer, a novel multi-stage transformer model that generates valid procedural material graphs, addressing complexity and heterogeneity challenges in the domain.

Findings

Outperforms alternative methods in graph and material quality.

Generates diverse procedural materials with complex spatial patterns.

Enables auto-completion and exploration of partial graphs.

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.