Interpretable procedural material graph generation via diffusion models from reference images

Xiaoyu Lv

doi:10.1007/s00371-025-04096-0

Interpretable procedural material graph generation via diffusion models from reference images

2025-07-17

0

PRE

AI

DOI：10.1007/s00371-025-04096-0

Original

Original request for help

Save

Abstract

En 中文

Procedural materials, generated through algorithmic processes, offer advantages such as resolution independence, editability, and real-time rendering capabilities. Despite these merits, constructing procedural material graphs remains a labor-intensive task. Recent advancements in generative neural networks, particularly diffusion models, have shown promise in automating this process. However, existing methods often struggle with issues related to generation quality, generalization, and interpretability. In this work, we introduce a novel approach for the interpretable generation of procedural material graphs from reference images using diffusion model. Our approach predicts individual nodes in reverse order, leveraging the generative capabilities of diffusion models to achieve significant improvements in generation quality, generalization, and interpretability. Specifically, we employ a two-stage framework: an adapter-based diffusion model predicts procedural nodes, forming an auxiliary graph, which is then refined using a DiffMat-based node parameter optimization method. To validate the effectiveness of our approach, we construct a fine-grained procedural material graph dataset containing extensive data and information defined at the node level. Our code and datasets are available at: https://github.com/InterS23/IPMGG .

Keywords:

Procedural material

Diffusion models

Texture generation

Procedural models

Interpretable procedural material graph generation via diffusion models from reference images

Abstract

Journal

Organization