Roof-GAN: Learning to Generate Roof Geometry and Relations for Residential Houses
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021(2021)
摘要
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.
更多查看译文
关键词
Roof-GAN,novel generative adversarial network,residential roof structures,roof primitives,structured roof model,raster images,facet segmentation,vector format,novel differentiable vectorizer,primitive raster geometry,primitive vector geometry,end-to-end architecture,diverse roof models,realistic roof models,structured geometry generation,generate Roof geometry,residential houses
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要