论文标题
节点图优化使用可区分的代理
Node Graph Optimization Using Differentiable Proxies
论文作者
论文摘要
基于图的程序材料在内容生产行业中无处不在。程序模型允许创建具有参数控制的感性材料，以灵活地进行外观编辑。但是，在构建模型和微调参数方面，设计特定材料是一个耗时的过程。先前的工作[Hu等。 2022; Shi等。 2020]引入了用于匹配目标材料样品的材料图优化框架。但是，这些先前的方法仅限于优化图表中的可区分函数。在本文中，我们提出了一个完全可区分的框架，即使图形的某些功能是不可差的，它也可以基于端梯度的材料图的优化。我们利用可区分的代理，这是一个非差异黑框函数的可区分近似器。我们使用框架将输出材料的结构和外观与目标材料匹配，并通过多阶段的可区分优化。与以前的工作相比，可区分的代理为材料外观匹配提供了更通用的优化解决方案。
Graph-based procedural materials are ubiquitous in content production industries. Procedural models allow the creation of photorealistic materials with parametric control for flexible editing of appearance. However, designing a specific material is a time-consuming process in terms of building a model and fine-tuning parameters. Previous work [Hu et al. 2022; Shi et al. 2020] introduced material graph optimization frameworks for matching target material samples. However, these previous methods were limited to optimizing differentiable functions in the graphs. In this paper, we propose a fully differentiable framework which enables end-to-end gradient based optimization of material graphs, even if some functions of the graph are non-differentiable. We leverage the Differentiable Proxy, a differentiable approximator of a non-differentiable black-box function. We use our framework to match structure and appearance of an output material to a target material, through a multi-stage differentiable optimization. Differentiable Proxies offer a more general optimization solution to material appearance matching than previous work.
