发表机构
University of California San Diego（加利福尼亚大学圣地亚哥分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究聚焦程序材质生成，核心方法是将其作为检索时的过程推理，利用专家演示、教程视频等提取轨迹并合成材质图。主要贡献是生成的材质编辑少、更符合专业策略，且相比先前系统有更好的生成和编辑性能。
AI 中文摘要
程序材质创建是数字内容创作、视觉效果和3D资产设计应用的基础。要获得高质量结果，不仅要复制节点图，还需理解专家构建材质的过程。我们将程序材质生成制定为对专家演示进行检索时的过程推理，将过程提升为超越仅图形合成的一流表示。具体而言，我们将专家工作流程表示为过程轨迹，使用基于预训练语言模型的ProcessSynthesizer合成与用户意图对齐的过程轨迹，并使用基于预训练语言模型的编译器将过程轨迹转换为可执行的Blender材质图。我们利用教程视频作为过程知识来源，通过自动视频分析工具提取文本轨迹。专家研究表明，反映专家演示生成的材质所需编辑更少，更符合专业设计策略。用户研究显示，与先前程序系统相比，我们的方法具有更好的生成和编辑性能。所有代码、模型和数据将在指定网址提供。
英文摘要
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
CommentsAccepted to ECCV 2026. Project page: https://materialapprentice.github.io
