Table 1.

Comparison of the EDU-AI with the studies adopting Pix2Pix in plan layout generation

StudyContext and functionScaleStructureRepresentationData set
Huang and Zheng (2018) HousingFloor planOnefold two directionalNine colors corresponding to the walkway, bedroom, living room, kitchen, toilet, dining room, balcony, window and door115 images grouped as 100 training and 15 validation data
Chaillou (2020) HousingFloor planOnefold one directionalNine colors corresponding to opening, footprint, entrance, living room, bedroom, closet, kitchen, bathroom and circulationAround 800 apartment plans as training data and more than 40 validation data
Liu et al. (2021) Educational, campusSite planOnefold one directionalApproximately 20 colors refer to the various components (architectural and landscape) of campuses387 images (85 university and 302 primary school layouts) as training data. Validation data is not mentioned
Tian (2021) Urban and regional planningSite planOnefold one directional16 colors corresponding to different types of functions such as residential and commercial4400 images grouped as 4000 training and 400 validation data
Liu et al. (2022) Private gardenSite planOne-fold one directional (iterative)Ten colors corresponding to boundary, entrance, water, site, central area, pathway, architecture, main landscape architecture, mountain and pavilion125 images grouped as 120 training and 5 validation data
EDU-AIEducational, classroomSingle room scaleTwofold one directionalEight colors corresponding to wall, door, opening, footprint, student desks, teacher desk, board and lockers162 images grouped as 144 training and 18 validation data
Sources: Huang and Zheng (2018), Chaillou (2020), Liu et al. (2021), Tian (2021) and Liu et al. (2022) 

or Create an Account

Close Modal
Close Modal