Issue |
SHS Web Conf.
Volume 194, 2024
The 6th ETLTC International Conference on ICT Integration in Technical Education (ETLTC2024)
|
|
---|---|---|
Article Number | 03003 | |
Number of page(s) | 6 | |
Section | Intelligent Information Design | |
DOI | https://doi.org/10.1051/shsconf/202419403003 | |
Published online | 26 June 2024 |
Intuitive space texture generation using hand tracking, speech recognition, and generative AI
Spatial Media Group, University of Aizu; Aizu-Wakamatsu, Fukushima ; Japan
* e-mail: donabe722@gmail.com
** e-mail: xilehence@gmail.com
This research aims to explore new methods of intuitively redesigning room interiors using gesture, speech, and generative AI. This approach represents a new approach to interior design, allowing users to easily customize appearance of a room through voice and hand gestures. This project investigates how hand tracking, speech recognition, and generative AI can be integrated to enable intuitive and user-friendly interior texture customization in virtual spaces. Previous studies on interior design using XR have mainly used augmented reality (AR) to relocate furniture. However, in these methods, the only way to select furniture textures is to search for them in prepared furniture. Our method uses hand-tracking and speech recognition to capture a user’s desired image and employs generative AI to realize these preferences in a VR environment. The process involves scanning real-world furniture and rooms and applying AI-generated textures based on what the user communicates. The system allows users to easily visualize room interiors and modify them according to their preferences. This can enhance the traditional room design process. This method is currently restricted to texture only, but 3D model generation AI could provide additional flexibility. This method also has the potential for collaborative design work by sharing an environment.
Key words: hand tracking / gesture interpretation / speech recognition / image-generative AI / virtual reality / interior design
© The Authors, published by EDP Sciences, 2024
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.