EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Mask2Former–FGMBRM: A Feature-Guided Building Segmentation Framework for Automated 3D Urban Environment Generation from Satellite Imagery

Ruben Dumlao Espejo Jr., Donghyun Woo, Hyunbin Choi, Joongrock Kim, Sunjin Yu

Remote Sensing · 06.11.2026 · 18 (21) · 3817

DOI: 10.3390/rs18213817 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 06.11.2026. Verfasst von Ruben Dumlao Espejo Jr. und 4 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: IITP (Institute of Information & Communications Technology Planning & Evaluation)–ITRC, Basic Science Research Program through the National Research Foundation of Korea.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Building-footprint errors can propagate into geospatial assets generated from remote-sensing imagery. This study evaluated Mask2Former–FGMBRM, which applies feature-guided residual refinement to Mask2Former query-mask predictions and integrates extracted footprints with documented terrain data and geospatial processing for footprint-based urban asset generation. Six models were evaluated on 518 WHU held-out images using common final references and metric definitions while retaining model-specific pipelines. The tune-selected Mask2Former baseline and FGMBRM achieved AP values of 72.03% and 73.49%, respectively, a 1.47-percentage-point improvement. FGMBRM also achieved 89.01% binary IoU and 91.86% object F1, leading these measures and AP among the six configurations, whereas SegFormer had the highest boundary F1. Controlled ablations showed metric-dependent trade-offs, with simpler variants leading selected outcomes and no consistent advantage from query-conditioned guidance. The original INRIA comparison remained limited. In a separate query-capacity diagnostic, AP at common maxDets = 100 increased from 20.66% to 23.96%, while retaining more outputs increased recall and false positives. The results support footprint-based urban asset generation and visualization, with remaining dense-scene and geometric limitations.

Förderung

  • IITP (Institute of Information & Communications Technology Planning & Evaluation)–ITRC
  • Basic Science Research Program through the National Research Foundation of Korea

Zitieren

APA

Jr., R. D. E., Woo, D., Choi, H., Kim, J., & Yu, S. (2026). Mask2Former–FGMBRM: A Feature-Guided Building Segmentation Framework for Automated 3D Urban Environment Generation from Satellite Imagery. Remote Sensing, 18(21), 3817. https://doi.org/10.3390/rs18213817

Vancouver

Jr. RDE, Woo D, Choi H, Kim J, Yu S. Mask2Former–FGMBRM: A Feature-Guided Building Segmentation Framework for Automated 3D Urban Environment Generation from Satellite Imagery. Remote Sensing. 2026;18(21):3817. doi:10.3390/rs18213817

BibTeX
@article{Jr2026,
  author = {Jr., Ruben Dumlao Espejo and Woo, Donghyun and Choi, Hyunbin and Kim, Joongrock and Yu, Sunjin},
  title = {Mask2Former–FGMBRM: A Feature-Guided Building Segmentation Framework for Automated 3D Urban Environment Generation from Satellite Imagery},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {21},
  pages = {3817},
  doi = {10.3390/rs18213817}
}
Kostenlos starten →