Context-Responsive Building Footprint Generation via Conditional Inpainting Using Latent Diffusion Models
Sustainability · 17.04.2026 · 18 (8) · 3987
DOI: 10.3390/su18083987 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sustainability, online erschienen am 17.04.2026. Verfasst von Eunseok Jang und 1 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Konkuk University.
Abstract (Originalsprache)
Generative AI has advanced rapidly in architectural design; however, existing building footprint generation models tend to emphasize stylistic exploration while insufficiently integrating site context as a fundamental physical constraint that facilitates alignment with the surrounding urban fabric. To address this limitation, this study proposes a context-responsive methodology for generating building footprints using a multi-layered four-channel representation of site conditions—including roads, sidewalks, adjacent buildings, and site boundaries—within a Latent Diffusion Model framework. The proposed approach encodes these physical conditions into a structured tensor and concatenates them directly to the U-Net input, enabling site context to function as an explicit spatial control variable during generation. An ablation study evaluated the effectiveness of the proposed contextual configuration. Compared with a single-channel model, the four-channel model achieved an 18.08% reduction in average pixel-wise information entropy, indicating a measurable decrease in generative uncertainty. Qualitative analyses further demonstrated that the enriched contextual input promotes geometrically coherent footprint configurations, such as context-responsive setbacks and spatial alignment with surrounding built forms. These findings suggest that structured multi-channel site information enhances contextual grounding in generative design processes and may contribute to more environmentally integrated and spatially coherent architectural outcomes.
Förderung
- Konkuk University
Zitieren
APA
Jang, E., & Kim, K. (2026). Context-Responsive Building Footprint Generation via Conditional Inpainting Using Latent Diffusion Models. Sustainability, 18(8), 3987. https://doi.org/10.3390/su18083987
Vancouver
Jang E, Kim K. Context-Responsive Building Footprint Generation via Conditional Inpainting Using Latent Diffusion Models. Sustainability. 2026;18(8):3987. doi:10.3390/su18083987
BibTeX
@article{Jang2026,
author = {Jang, Eunseok and Kim, Kyunghwan},
title = {Context-Responsive Building Footprint Generation via Conditional Inpainting Using Latent Diffusion Models},
journal = {Sustainability},
year = {2026},
volume = {18},
number = {8},
pages = {3987},
doi = {10.3390/su18083987}
}
EUVIMED