Search papers, labs, and topics across Lattice.
This paper introduces a novel approach to procedural material generation that emphasizes process reasoning by utilizing expert demonstrations rather than relying solely on static node graphs. By representing expert workflows as process traces, the authors leverage a pretrained LLM-based ProcessSynthesizer to align user intent with expert construction steps, and a Compiler to convert these traces into executable Blender material graphs. The results from expert and user studies demonstrate that materials generated through this method require fewer edits and better align with professional design strategies compared to traditional procedural systems.
Expert-driven procedural material generation reduces editing needs and aligns closely with professional design practices, outperforming traditional methods.
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
