EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DiffDesign: Controllable diffusion with meta prior for efficient interior design generation

Tao Geng iD, Yuxuan Yang

PLOS One · 04.09.2025 · 20 (9) · e0331240

DOI: 10.1371/journal.pone.0331240 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 04.09.2025. Verfasst von Tao Geng und 1 weiteren Autor:innen. Beteiligte Einrichtung: Nanjing Forestry University, Nanjing, China. Hauptthemen laut MEDLINE: Interior Design and Furnishings, Machine Learning. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Interior design is a complex and creative discipline involving aesthetics, functionality, ergonomics, and materials science. Effective solutions must meet diverse requirements, typically producing multiple deliverables such as renderings and design drawings from various perspectives. Consequently, interior design processes are often inefficient and demand significant creativity. With advances in machine learning, generative models have emerged as a promising means of improving efficiency by creating designs from text descriptions or sketches. However, few generative works focus on interior design, leading to substantial discrepancies between outputs and practical needs, such as differences in size, spatial scope, and the lack of controllable generation quality. To address these challenges, we propose DiffDesign, a controllable diffusion model with meta priors for efficient interior design generation. Specifically, we utilize the generative priors of a 2D diffusion model pre-trained on a large image dataset as our rendering backbone. We further guide the denoising process by disentangling cross-attention control over design attributes, such as appearance, pose, and size, and introduce an optimal transfer-based alignment module to enforce view consistency. Simultaneously, we construct an interior design-specific dataset, DesignHelper, consisting of over 400 solutions across more than 15 spatial types and 15 design styles. This dataset helps fine-tune DiffDesign. Extensive experiments conducted on various benchmark datasets demonstrate the effectiveness and robustness of DiffDesign.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Interior Design and FurnishingsMachine LearningHumansAlgorithms

Autor:innen und Institutionen

  • Nanjing Forestry University, Nanjing, China.

ORCID-Profile: Tao Geng

Zitieren

APA

Geng, T., & Yang, Y. (2025). DiffDesign: Controllable diffusion with meta prior for efficient interior design generation. PLOS One, 20(9), e0331240. https://doi.org/10.1371/journal.pone.0331240

Vancouver

Geng T, Yang Y. DiffDesign: Controllable diffusion with meta prior for efficient interior design generation. PLOS One. 2025;20(9):e0331240. doi:10.1371/journal.pone.0331240

BibTeX
@article{Geng2025,
  author = {Geng, Tao and Yang, Yuxuan},
  title = {DiffDesign: Controllable diffusion with meta prior for efficient interior design generation},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {9},
  pages = {e0331240},
  doi = {10.1371/journal.pone.0331240}
}
Kostenlos starten →