VLMaterial: Procedural Material Generation with Large Vision-Language Models
This work addresses the challenge of creating procedural materials for computer graphics, which typically requires professional expertise, by automating the process for users in this domain.
The paper tackles the problem of generating procedural materials from input images by fine-tuning a vision-language model to produce Python programs, and demonstrates that their method outperforms previous approaches on synthetic and real-world examples.
Procedural materials, represented as functional node graphs, are ubiquitous in computer graphics for photorealistic material appearance design. They allow users to perform intuitive and precise editing to achieve desired visual appearances. However, creating a procedural material given an input image requires professional knowledge and significant effort. In this work, we leverage the ability to convert procedural materials into standard Python programs and fine-tune a large pre-trained vision-language model (VLM) to generate such programs from input images. To enable effective fine-tuning, we also contribute an open-source procedural material dataset and propose to perform program-level augmentation by prompting another pre-trained large language model (LLM). Through extensive evaluation, we show that our method outperforms previous methods on both synthetic and real-world examples.