A Deep Learning Approach for Interior Designing of Apartment Building Architecture using U2 Net
Gaurav Kumar, Ashish Kumar, Rahul · 2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS) · 2022
The introduction of Deep Learning in computer technology has mastered various fields of study like medical, Banking, Finance etc. but the field of construction is lagging behind by still requiring some manual work. Apartment building designing is a complex task which requires professional architects and various tools. It would be easier and more fascinating if one can get the interior design just by having the shape of the land area. By considering this, a model has been proposed to serve the purpose of designing apartment architecture using generative adversarial networks. This study describes a system consisting of two sequential U2Net [13] based GAN models in which the first model has been trained for printing footprint of a building whereas second one for showing segmented sections for various areas of apartment.