| spelling |
oapen-20.500.12657-890382024-04-03T02:22:43Z Chapter Reflecting Users’ Physical Characteristics in Spatial Visualization Chae, Sumin Jo, Hayoung Kim, Bomin Lee, Jin-Kook Generative AI Physical Characteristics Elderly-friendly Bathroom Detailed Modeling thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence This paper aims to quickly and precisely visualize remodeled design images based on image generation AI so that they can be used as alternative images in the early stages of design. In order to create a space image suitable for the user, the contents of the text are proceeded as follows. Bathrooms with many accidents in the space were selected as the target space, and users were designated as elderly people with many physical changes. Learning image data for additional training was self-generated according to the user's body characteristics, and the learning data focused on musculoskeletal aging among the body characteristics of elderly users. When the image was generated using additional training models, it was confirmed that a meaningful spatial image was created for musculoskeletal aging users, and it can be expected that the spatial image for spatial remodeling can be obtained quickly and accurately without the help of experts through subsequent studies to make it easier for general users 2024-04-02T15:44:26Z 2024-04-02T15:44:26Z 2023 chapter ONIX_20240402_9791221502893_7 2704-5846 9791221502893 https://library.oapen.org/handle/20.500.12657/89038 eng Proceedings e report application/pdf n/a 9791221502893_94.pdf https://books.fupress.com/doi/capitoli/979-12-215-0289-3_94 Firenze University Press 10.36253/979-12-215-0289-3.94 10.36253/979-12-215-0289-3.94 bf65d21a-78e5-4ba2-983a-dbfa90962870 9791221502893 137 7 Florence open access
|
| description |
This paper aims to quickly and precisely visualize remodeled design images based on image generation AI so that they can be used as alternative images in the early stages of design. In order to create a space image suitable for the user, the contents of the text are proceeded as follows. Bathrooms with many accidents in the space were selected as the target space, and users were designated as elderly people with many physical changes. Learning image data for additional training was self-generated according to the user's body characteristics, and the learning data focused on musculoskeletal aging among the body characteristics of elderly users. When the image was generated using additional training models, it was confirmed that a meaningful spatial image was created for musculoskeletal aging users, and it can be expected that the spatial image for spatial remodeling can be obtained quickly and accurately without the help of experts through subsequent studies to make it easier for general users
|
