Future Designer - Generative AI Meets Interior Design
Abstract
Interior design visualization plays a crucial role in property evaluation, yet traditional methods, such as professional consultations and 3D modeling, are often time-consuming and costly. This paper introduces an AI-driven system that enables room customization in real time through automated image generation and intelligent furniture search. Our solution democratizes design visualization by reducing dependence on professional services, empowering users to instantly tailor spaces to their preferences during property comparisons. This approach enhances decision-making efficiency while offering scalable personalization, redefining how individuals engage with potential living environments. Importantly, the implementation relies entirely on open-source models and is optimized for consumer-class GPU execution. The system architecture also supports facile scaling, making it suitable for companies seeking to integrate a customizable interior design feature, potentially linked to their specific furniture catalogues.
Cite
Text
Nowicki et al. "Future Designer - Generative AI Meets Interior Design." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2025. doi:10.1007/978-3-032-06129-4_42Markdown
[Nowicki et al. "Future Designer - Generative AI Meets Interior Design." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2025.](https://mlanthology.org/ecmlpkdd/2025/nowicki2025ecmlpkdd-future/) doi:10.1007/978-3-032-06129-4_42BibTeX
@inproceedings{nowicki2025ecmlpkdd-future,
title = {{Future Designer - Generative AI Meets Interior Design}},
author = {Nowicki, Filip and Charlinski, Arkadiusz and Wójtowicz, Andrzej},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2025},
pages = {516-520},
doi = {10.1007/978-3-032-06129-4_42},
url = {https://mlanthology.org/ecmlpkdd/2025/nowicki2025ecmlpkdd-future/}
}