Reflecting Process Expertise in Procedural Material Generation
Quick Answer
The study introduces a novel approach to procedural material generation using a pretrained LLM-based ProcessSynthesizer and Compiler, which enhances material creation by reflecting expert workflows.
Quick Take
The study introduces a novel approach to procedural material generation using a pretrained LLM-based ProcessSynthesizer and Compiler, which enhances material creation by reflecting expert workflows. User studies indicate that this method yields superior results in generation and editing compared to traditional static artifact methods, with fewer required edits and closer alignment to professional design strategies.
Key Points
- Introduces ProcessSynthesizer and Compiler for procedural material generation.
- Utilizes expert workflows as process traces for improved material creation.
- User studies show fewer edits needed and better alignment with design strategies.
- Results outperform previous procedural systems in generation and editing performance.
- All code, models, and data will be publicly available.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Procedural material creation underpins applications in digital content creation, visual effects, and 3D asset design. Achieving high-quality results requires more than reproducing node graphs -- it demands understanding the process by which experts construct materials. We formulate procedural material generation as retrieval-time process reasoning over expert demonstrations, elevating process to a first-class representation beyond graph-only synthesis. Concretely, we represent expert workflows as process traces: textual records of construction steps, parameters, and design intent. To instantiate this idea, we use a pretrained LLM-based ProcessSynthesizer to synthesize a process trace aligned with a user's intent and a pretrained LLM-based Compiler to ground the process trace into an executable Blender material graph. Because procedural expertise is most naturally conveyed through demonstrations, we leverage tutorial videos as a source of process knowledge and extract textual, LLM-compatible traces using automated video analysis tools. In an expert study with five Blender artists (avg. 7.5 years of experience), materials generated by reflecting expert demonstrations were found to produce workflows requiring fewer edits, and more closely match professional design strategies than methods operating solely on static artifacts. A user study with 150 participants further shows that our approach achieves superior generation and editing performance compared to prior procedural systems. All code, models, and data will be available at this https URL
| Comments: | Accepted to ECCV 2026. Project page: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2607.13318 [cs.CV] |
| (or arXiv:2607.13318v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2607.13318 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kunal Gupta [view email]
[v1]
Tue, 14 Jul 2026 22:59:32 UTC (14,282 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.