基于样例驱动的BSP和变分自编码器的多领域层次生成和草图融合
Multi-Domain Level Generation and Blending with Sketches via Example-Driven BSP and Variational Autoencoders
摘要：
通过机器学习（PCGML）的程序内容生成已经证明了其作为内容和游戏创建方法的有用性，并且已经被证明能够支持人类的创造力。创造力的一个重要方面是组合创造力，或在领域之间和跨领域的思想和概念的重组，适应和重用。在本文中，我们提出了一个PCGML方法的水平生成，能够重组，适应和重用结构模式，从几个领域近似看不见的领域。我们扩展了以前的工作，涉及到的例子驱动的二进制空间划分重组和重用模式在多个领域，并纳入变分自编码器（VAE）生成看不见的结构。我们评估我们的方法混合在$7$域和这些域的子集。我们表明，我们的方法是能够混合域在一起，同时保留结构组件。此外，通过使用不同的训练域组，我们的方法能够生成1）再现和捕获目标域的特征的级别，以及2）具有与输入域截然不同的属性的级别。
英文摘要：
Procedural content generation via machine learning (PCGML) has demonstrated its usefulness as a content and game creation approach, and has been shown to be able to support human creativity. An important facet of creativity is combinational creativity or the recombination, adaptation, and reuse of ideas and concepts between and across domains. In this paper, we present a PCGML approach for level generation that is able to recombine, adapt, and reuse structural patterns from several domains to approximate unseen domains. We extend prior work involving example-driven Binary Space Partitioning for recombining and reusing patterns in multiple domains, and incorporate Variational Autoencoders (VAEs) for generating unseen structures. We evaluate our approach by blending across $7$ domains and subsets of those domains. We show that our approach is able to blend domains together while retaining structural components. Additionally, by using different groups of training domains our approach is able to generate both 1) levels that reproduce and capture features of a target domain, and 2) levels that have vastly different properties from the input domain.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
