EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Advancing Interior Design with AI: Controllable Stable Diffusion for Panoramic Image Generation

Wanggong Yang, Congcong Wang, Luxiang Liu, Shuying Dong, Yifei Zhao

Buildings · 21.04.2025 · 15 (8) · 1391

DOI: 10.3390/buildings15081391 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Buildings, online erschienen am 21.04.2025. Verfasst von Wanggong Yang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Beijing Municipal High-Level Faculty Development Support Program on “Research on the Digital Preservation and Innovative Development of Beijing’s Central Axis…, Beijing Institute of Graphic Communication Project on “Application research on creating immersive restaurants based on 3D holographic projection technology”, Youth Support Program of Beijing Institute of Graphic Communication on ”A Study on the Digital Representation of Chinese Cultural Visual Symbols”.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

AI-driven technologies have significantly advanced panoramic image generation in interior design; however, existing methods often lack controllability and consistency in rendering high-quality, coherent panoramas. To address these limitations, the study proposes CSD-Pano, a controllable and stable diffusion framework tailored for panoramic interior design generation. The study also introduces PSD-4, a curated dataset of panoramic scenes covering diverse interior decoration styles to support training and evaluation. CSD-Pano enables fine-grained control over aesthetic attributes, layout coherence, and stylistic consistency. Furthermore, the study designs a panoramic loss function that enhances spatial coherence, geometric alignment, and perceptual fidelity. Extensive qualitative and quantitative experiments demonstrate that CSD-Pano achieves superior performance compared to existing baselines, with significant improvements in SSIM and LPIPS metrics. These results validate the effectiveness of our approach in advancing automated panoramic interior design.

Förderung

  • Beijing Municipal High-Level Faculty Development Support Program on “Research on the Digital Preservation and Innovative Development of Beijing’s Central Axis…
  • Beijing Institute of Graphic Communication Project on “Application research on creating immersive restaurants based on 3D holographic projection technology”
  • Youth Support Program of Beijing Institute of Graphic Communication on ”A Study on the Digital Representation of Chinese Cultural Visual Symbols”

Zitieren

APA

Yang, W., Wang, C., Liu, L., Dong, S., & Zhao, Y. (2025). Advancing Interior Design with AI: Controllable Stable Diffusion for Panoramic Image Generation. Buildings, 15(8), 1391. https://doi.org/10.3390/buildings15081391

Vancouver

Yang W, Wang C, Liu L, Dong S, Zhao Y. Advancing Interior Design with AI: Controllable Stable Diffusion for Panoramic Image Generation. Buildings. 2025;15(8):1391. doi:10.3390/buildings15081391

BibTeX
@article{Yang2025,
  author = {Yang, Wanggong and Wang, Congcong and Liu, Luxiang and Dong, Shuying and Zhao, Yifei},
  title = {Advancing Interior Design with AI: Controllable Stable Diffusion for Panoramic Image Generation},
  journal = {Buildings},
  year = {2025},
  volume = {15},
  number = {8},
  pages = {1391},
  doi = {10.3390/buildings15081391}
}
Kostenlos starten →