EUVIMEDEUVIMED entdecken
Crossref

DiffVector: Boosting Diffusion Framework for Building Vector Extraction From Remote Sensing Images

Bingnan Yang, Mi Zhang, Yuanxin Zhao, Zhili Zhang, Xiangyun Hu, Jianya Gong

IEEE Transactions on Geoscience and Remote Sensing · 2025 · 63 · 1-19

DOI: 10.1109/tgrs.2025.3528474 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Geoscience and Remote Sensing, 2025. Verfasst von Bingnan Yang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 89 Literaturangaben. Gefördert von: Key Research and Development Program of Hubei Province, National Natural Science Foundation of China, Major Program of the National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Building vector maps play an essential role in many remote sensing (RS) applications, thereby boosting the deep learning (DL)-based automatic building vector extraction methods. These approaches have achieved pleasant overall accuracy, but their predict-style framework struggles with perceiving subtle details within a tiny area, such as corners and adjacent walls. In this study, we introduce a denoising diffusion framework called DiffVector to generate representations for direct building vector extraction from the RS images. First, we develop a hierarchical diffusion transformer (HiDiT) to conditionally generate robust representations for detecting nodes and extracting corresponding features. The conditions of HiDiT are multilevel boundary attentive maps encoded from input RS images through a topology-concentrated Swin Transformer (TCSwin). Subsequently, an edge-biased graph diffusion transformer (EGDiT) takes extracted node features as conditions to produce new visual descriptors for the adjacency matrix prediction. In EGDiT, we replace the standard self-attention (SA) operation with an edge-biased attention (EBA) to inject edge information for training stabilization. Furthermore, given typical challenges of training difficulty and weak perceptive ability in convectional diffusion paradigms, we conduct an isomorphic training strategy (ITS), ensuring that the training procedures of both HiDiT and EGDiT precisely mirror the inference phase. Quantitative and qualitative experiments have evidently demonstrated that DiffVector can achieve competitive performance compared with existing modern approaches, especially in the metrics assessing topology quality.

Förderung

  • Key Research and Development Program of Hubei Province
  • National Natural Science Foundation of China
  • Major Program of the National Natural Science Foundation of China
  • Special Fund of Hubei Luojia Laboratory

Zitieren

APA

Yang, B., Zhang, M., Zhao, Y., Zhang, Z., Hu, X., & Gong, J. (2025). DiffVector: Boosting Diffusion Framework for Building Vector Extraction From Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing, 63, 1-19. https://doi.org/10.1109/tgrs.2025.3528474

Vancouver

Yang B, Zhang M, Zhao Y, Zhang Z, Hu X, Gong J. DiffVector: Boosting Diffusion Framework for Building Vector Extraction From Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing. 2025;63:1-19. doi:10.1109/tgrs.2025.3528474

BibTeX
@article{Yang2025,
  author = {Yang, Bingnan and Zhang, Mi and Zhao, Yuanxin and Zhang, Zhili and Hu, Xiangyun and Gong, Jianya},
  title = {DiffVector: Boosting Diffusion Framework for Building Vector Extraction From Remote Sensing Images},
  journal = {IEEE Transactions on Geoscience and Remote Sensing},
  year = {2025},
  volume = {63},
  pages = {1--19},
  doi = {10.1109/tgrs.2025.3528474}
}
Kostenlos starten →