Multiple Layout Design Generation via a GAN-Based Method with Conditional Convolution and Attention

DOI Web Site 参考文献13件
  • ZHU Xing
    School of Electronic and Information Engineering, South China University of Technology
  • LIU Yuxuan
    Waseda University
  • LIANG Lingyu
    School of Electronic and Information Engineering, South China University of Technology Ministry of Education Key Laboratory of Computer Network and Information Integration, Southeast University Pazhou Lab
  • WANG Tao
    Fujian Provincial Key Laboratory of Information Processing and Intelligent Control, College of Computer and Control Engineering, Minjiang University The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions, Wuyi University
  • LI Zuoyong
    Fujian Provincial Key Laboratory of Information Processing and Intelligent Control, College of Computer and Control Engineering, Minjiang University
  • DENG Qiaoming
    School of Architecture, South China University of Technology
  • LIU Yubo
    School of Architecture, South China University of Technology

抄録

<p>Recently, many AI-aided layout design systems are developed to reduce tedious manual intervention based on deep learning. However, most methods focus on a specific generation task. This paper explores a challenging problem to obtain multiple layout design generation (LDG), which generates floor plan or urban plan from a boundary input under a unified framework. One of the main challenges of multiple LDG is to obtain reasonable topological structures of layout generation with irregular boundaries and layout elements for different types of design. This paper formulates the multiple LDG task as an image-to-image translation problem, and proposes a conditional generative adversarial network (GAN), called LDGAN, with adaptive modules. The framework of LDGAN is based on a generator-discriminator architecture, where the generator is integrated with conditional convolution constrained by the boundary input and the attention module with channel and spatial features. Qualitative and quantitative experiments were conducted on the SCUT-AutoALP and RPLAN datasets, and the comparison with the state-of-the-art methods illustrate the effectiveness and superiority of the proposed LDGAN.</p>

収録刊行物

参考文献 (13)*注記

もっと見る

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ