Design Dreamer: ControlNet Based Generative AI Application for Interior Designing

Param Dhingana¹ , Vinamra Khandelwal² , Sudeep Ganguly³ , Dipti Chauhan⁴

1. Dept. of Artificial Intelligence and Data Science, Prestige Institute of Engineering Management & Research, Indore, India.
2. Dept. of Artificial Intelligence and Data Science, Prestige Institute of Engineering Management & Research, Indore, India.
3. Dept. of Artificial Intelligence and Data Science, Prestige Institute of Engineering Management & Research, Indore, India.
4. Dept. of Artificial Intelligence and Data Science, Prestige Institute of Engineering Management & Research, Indore, India.

Section:Research Paper, Product Type: Journal-Paper
Vol.12 , Issue.3 , pp.1-7, Jun-2024

Online published on Jun 30, 2024

Copyright © Param Dhingana, Vinamra Khandelwal, Sudeep Ganguly, Dipti Chauhan . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
 

View this paper at   Google Scholar | DPI Digital Library

XML View     PDF Download

How to Cite this Paper

188 Views    201 Downloads    19 Downloads

Abstract :
The emergence of state-of-the-art technologies, which powers the process of Generative AI, is now altering the interior design landscape. This study starts with Design Dreamer, the latest application among all, which gives users an opportunity to dream about and customize their living space in a remarkable way. Design Dreamer makes it possible to implement the most advanced systems in the ControlNet family that provide best-in-class immersive and interactive experience for the end users. Users share their room photos, give a purpose of their preferred design styles and room type then they get digital replays, which are AI-generated, and they are capable of visually reflecting what a person wants to see in their room. Our approach involves a multi-step procedure, uploading images, choosing style preferences, using the ControlNet Hough Model by calling through Replicate API, and efficiently retrieving the generated image when users pose a design. Key findings of our research demonstrate that Design Dreamer significantly enhances image quality and provides a unique output each time. The significance of this research lies in its potential to leverage Diffusion and ControlNet based models for their applications in Interior Design industry.

Key-Words / Index Term :
Generative AI, Interior Design, State-of-The-Art Technology, Image-Processing, Text-to-Image Generation, Image-to-Image Generation, Image-to-Image Transformation, Stable-Diffusion, ControlNet, AI-Powered Design Tools, Diffusion Models

References :
[1] M. A. Nielsen, "Reinventing discovery: The new era of networked science," Princeton University Press, 2011.
[2] Pavllo, Dario & Lucchi, Aurelien & Hofmann, Thomas. Controlling Style and Semantics in Weakly-Supervised Image Generation, 2020. 10.1007/978-3-030-58539-6_29.
[3] Rawas, Soha. “AI: the future of humanity. Discover Artificial Intelligence”, Vol.4, 2024. 4. 25. 10.1007/s44163-024-00118-3.
[4] J. D. Curtó, I. C. Zarza, Fernando de la Torre, Irwin King, Michael R. Lyu, “High-resolution Deep Convolutional Generative Adversarial Networks”, Vol.18, 2020. DOI: https://arxiv.org/abs/1711.06491
[5] Seongmin Lee, Benjamin Hoover, Hendrik Strobelt, Zijie J. Wang, ShengYun Peng, Austin Wright, Kevin Li, Haekyu Park, Haoyang Yang, Duen Horng Chau, “Diffusion Explainer: Visual Explanation for Text-to-image Stable Diffusion”, Vol.2, 2023. DOI: https://arxiv.org/abs/2305.03509
[6] Diana Moses "A Survey of Techniques for Web Personalization". International Journal of Computer Trends and Technology (IJCTT) www.ijcttjournal.org. Published by Seventh Sense Research Group. October, Vol.52, Issue.1, pp.29-37, 2017. ISSN:2231-2803.
[7] Landwehr, Julius Peter et al. “Design Knowledge for Deep-Learning-Enabled Image-Based Decision Support Systems: Evidence From Power Line Maintenance Decision-Making.” Business & Information Systems Engineering, Vol.64,6, pp.707–728, 2022. Doi:10.1007/s12599-022-00745-z.
[8] Monkiz Khasreen, Philip F. G. Banfill, Gillian Menzies, “D. A. Cole, "Environmental impact of buildings: A review of history, current practice, and future trends," The Construction Specifier, Vol.1, Issue.3, pp.674-701, 2009. DOI: http://dx.doi.org/10.3390/su1030674
[9] Tunjung Atmadi, Ali Ramadhan, “The Role of Computer-Aided Design and Visual Simulation in Interior Design”, Vol.44, No.2, 2023. DOI: http://dx.doi.org/10.52783/tjjpt.v44.i2.150.
[10] Punam Mahesh Ingale, The importance of Digital Image Processing and its applications, International Journal of Scientific Research in Computer Science and Engineering, Vol.06, Issue.01, pp.31-32, 2018.A. M. Turing, "Computing machinery and intelligence," Mind, new series, Vol.59, No.236, pp.433-460, 1950.
[11] F. Rosenblatt, " The perceptron: A probabilistic model for information storage and organization in the brain" Psychological review, Vol.65, No.6, pp.386-408, 1958.
[12] I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, "Generative adversarial networks," arXiv preprint arXiv:1406.2661, 2014.
[13] Humza Naveed, Asad Ullah Khan, Shi Qiu, Muhammad Saqib, Saeed Anwar, Muhammad Usman, Naveed Akhtar, Nick Barnes, Ajmal Mian “A Comprehensive Overview of Large Language Models”, arXiv:2307.06435v3. 2023.
[14] Yuanbo Wang, Unaiza Ahsan, Hanyan Li and Matthew Hagen (2022), "A Comprehensive Review of Modern Object Segmentation Approaches", Foundations and Trends® in Computer Graphics and Vision: Vol.13, No.2-3, pp.111-283, 2022. http://dx.doi.org/10.1561/0600000097
[15] Niklas Deckers, M. Frobe, J. Kiesel, Gianluca Pandolfo, Christopher Schroder, Benno Stein, “The Infine Index: Information Retrieval on Generative Text-to-Image Models”, arXiv:2212.07476v2. 2022.
[16] Hanna, Dena.. The Use of Artificial Intelligence Art Generator "Midjourney" in Artistic and Advertising Creativity. 4. pp.42-58, 2023. DOI: 10.21608/jdsaa.2023.169144.1231.
[17] Eugenio Lomurno, Matteo D`Oria, Matteo Matteucci, “Stable Diffusion Dataset Generation for Downstream Classification Tasks”, 2024. DOI: https://arxiv.org/abs/2405.02698v1
[18] Shijie Hao, Yuan Zhou, Yanrong Guo, “A Brief Survey on Semantic Segmentation with Deep Learning”, Vol.406, pp.302-321, 2020. DOI: https://doi.org/10.1016/j.neucom.2019.11.118
[19] Ziyi Qin, A Multimodal Diffusion-based Interior Design AI with ControlNet. Journal of Artificial Intelligence Practice, Vol.7, pp.162-165, 2024. DOI: http://dx.doi.org/10.23977/jaip.2024.070124
[20] Roshani. L.Jain, Lubdha M. Bendale, Gayatri D. Patil, Image Enhancement Using Different Techniques, International Journal of Scientific Research in Computer Science and Engineering, Vol.6, Issue.1, pp.73-76, 2018.