arXiv 2003.069882020-03-16cs.CV

House-GAN：用于图约束房屋布局生成的关系生成对抗网络

House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation

Simon Fraser University（西蒙弗雷泽大学）；Autodesk Research（欧特克研究院）

Nelson Nauata, Kai-Hung Chang, Chin-Yi Cheng, Greg Mori, Yasutaka Furukawa

摘要：

本文提出了一种新的图约束生成对抗网络，其生成器和查询器都建立在关系结构上。其主要思想是将约束编码到其关系网络的图结构中。我们已经展示了所提出的用于新房屋布局生成问题的架构，其任务是将架构约束作为图（即，房间的数量和类型及其空间相邻性），并产生一组轴对齐的房间边界框。我们用三个指标来衡量生成的房屋布局的质量：真实性，多样性和与输入图约束的兼容性。我们对117，000个真实平面图图像的定性和定量评估表明，所提出的方法优于现有的方法和基线。我们将公开分享我们所有的代码和数据。

英文摘要：

This paper proposes a novel graph-constrained generative adversarial network, whose generator and discriminator are built upon relational architecture. The main idea is to encode the constraint into the graph structure of its relational networks. We have demonstrated the proposed architecture for a new house layout generation problem, whose task is to take an architectural constraint as a graph (i.e., the number and types of rooms with their spatial adjacency) and produce a set of axis-aligned bounding boxes of rooms. We measure the quality of generated house layouts with the three metrics: the realism, the diversity, and the compatibility with the input graph constraint. Our qualitative and quantitative evaluations over 117,000 real floorplan images demonstrate that the proposed approach outperforms existing methods and baselines. We will publicly share all our code and data.

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。

摘要：

英文摘要：

相关论文