论文标题
屋顶式：学会生成屋顶几何形状和住宅关系
Roof-GAN: Learning to Generate Roof Geometry and Relations for Residential Houses
论文作者
论文摘要
本文介绍了屋顶工具，这是一种新颖的生成对抗网络，该网络生成了住宅屋顶结构的结构化几何形状，作为一组屋顶原始的原始人及其关系。鉴于原语的数量，发电机将产生一个结构化的屋顶模型作为图，该模型由1）原始几何形状作为每个节点的栅格图像，编码刻面分割和角度； 2）在每个边缘处的主要colinear/共晶型关系； 3）在每个节点上以矢量格式的原始几何形状，在实施关系时由新颖的可区分矢量器生成。训练了鉴别器，以评估完全端到端体系结构中原始的栅格几何形状，原始关系和原始矢量几何形状。定性和定量评估证明了我们方法在本文中提出的新的指标在结构化几何形状生成的任务中提出了一种新的指标，在竞争方法上产生多样化和现实的屋顶模型的有效性。代码和数据可在https://github.com/yi-ming-qian/forgan上找到。
This paper presents Roof-GAN, a novel generative adversarial network that generates structured geometry of residential roof structures as a set of roof primitives and their relationships. Given the number of primitives, the generator produces a structured roof model as a graph, which consists of 1) primitive geometry as raster images at each node, encoding facet segmentation and angles; 2) inter-primitive colinear/coplanar relationships at each edge; and 3) primitive geometry in a vector format at each node, generated by a novel differentiable vectorizer while enforcing the relationships. The discriminator is trained to assess the primitive raster geometry, the primitive relationships, and the primitive vector geometry in a fully end-to-end architecture. Qualitative and quantitative evaluations demonstrate the effectiveness of our approach in generating diverse and realistic roof models over the competing methods with a novel metric proposed in this paper for the task of structured geometry generation. Code and data are available at https://github.com/yi-ming-qian/roofgan .
