Neurosymbolic Models for Computer Graphics
Neurosymbolic Models for Computer Graphics
复制标题
DOI：
10.1111/cgf.14775
复制
发表时间：
2023-04
影响因子：
2.5
通讯作者：
Daniel Ritchie;Paul Guerrero;R. K. Jones;N. Mitra;Adriana Schulz;Karl D. D. Willis-Karl-D.-D.-Willis-2269914;Jiajun Wu
中科院分区：
文献类型：
--
作者：
Daniel Ritchie;Paul Guerrero;R. K. Jones;N. Mitra;Adriana Schulz;Karl D. D. Willis-Karl-D.-D.-Willis-2269914;Jiajun Wu
过程模型（即输出视觉数据的符号程序）是一种历史上流行的表示图形内容（如植被、建筑物、纹理等）的方法。它们具有许多优点：可解释的设计参数、随机变化、高质量的输出、紧凑的表示形式等等。但它们也有一些局限性，比如从头开始创建一个过程模型很困难。最近，基于人工智能的方法，尤其是神经网络，在创建图形内容方面变得流行起来。这些技术允许用户直接指定他们想要创建的物品的期望属性（通过示例、约束条件或目标），而搜索、优化或学习算法则负责处理细节。然而，这种易用性是有代价的，因为通常很难解释或操作这些表示形式。在这份最新技术报告中，我们总结了计算机图形学中神经符号模型的研究：这些方法结合了人工智能和符号程序的优势来表示、生成和操作视觉数据。我们综述了近期将这些技术应用于表示二维形状、三维形状以及材质和纹理的工作。在此过程中，我们将每一项先前的工作置于神经符号模型的统一设计空间中，这有助于揭示未充分探索的领域以及未来研究的机会。
Procedural models (i.e. symbolic programs that output visual data) are a historically‐popular method for representing graphics content: vegetation, buildings, textures, etc. They offer many advantages: interpretable design parameters, stochastic variations, high‐quality outputs, compact representation, and more. But they also have some limitations, such as the difficulty of authoring a procedural model from scratch. More recently, AI‐based methods, and especially neural networks, have become popular for creating graphic content. These techniques allow users to directly specify desired properties of the artifact they want to create (via examples, constraints, or objectives), while a search, optimization, or learning algorithm takes care of the details. However, this ease of use comes at a cost, as it's often hard to interpret or manipulate these representations. In this state‐of‐the‐art report, we summarize research on neurosymbolic models in computer graphics: methods that combine the strengths of both AI and symbolic programs to represent, generate, and manipulate visual data. We survey recent work applying these techniques to represent 2D shapes, 3D shapes, and materials & textures. Along the way, we situate each prior work in a unified design space for neurosymbolic models, which helps reveal underexplored areas and opportunities for future research.