CVJul 14

Reflecting Process Expertise in Procedural Material Generation

arXiv:2607.1331810.6h-index: 12
Predicted impact top 37% in CV · last 90 daysOriginality Incremental advance
AI Analysis

For digital content creators and 3D artists, this work improves procedural material generation by incorporating expert process knowledge, reducing manual editing effort.

This work introduces a method for procedural material generation that leverages expert process traces extracted from tutorial videos, using an LLM-based ProcessSynthesizer and Compiler. In expert and user studies, the approach produces workflows requiring fewer edits and achieving superior generation and editing performance compared to prior systems.

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 https://materialapprentice.github.io

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes