Interior Space Design and Automatic Layout Method Based on CNN

WeiPing Wu, Yanshun Feng and Man Fai Leung

Mathematical Problems in Engineering, 2022, vol. 2022, 1-14

Abstract: With the rapid rise in the number of people buying houses, the demand for interior space design has also increased accordingly. The diversification of existing room types and the diversity of the public’s perception of fashion make interior designers in short supply. The future of computer science and technology in the field of automatic design of indoor areas will be immeasurable. This paper proposes an automatic layout method for spatial area design based on convolutional neural networks (CNN). CNN methods are a fast and efficient method. By mimicking the designer’s design process, it proposes a two-stage algorithm that defines the room first and the wall later, and the algorithm also provides a large-scale dataset called RPLAN that contains more than 80,000 interior layout plans from real residential buildings. Starting from the prediction living room, the automatic layout of the indoor areas is completed by iteration. A large number of empirical results show that the interior area design effect of this method is comparable to the interior design floor plan of professional designers.

Date: 2022
References: Add references at CitEc
Citations:

Downloads: (external link)
http://downloads.hindawi.com/journals/mpe/2022/8006069.pdf (application/pdf)
http://downloads.hindawi.com/journals/mpe/2022/8006069.xml (application/xml)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hin:jnlmpe:8006069

DOI: 10.1155/2022/8006069

Access Statistics for this article

More articles in Mathematical Problems in Engineering from Hindawi
Bibliographic data for series maintained by Mohamed Abdelhakeem ().