EUVIMEDEUVIMED entdecken
Crossref

Vector Map as Language: Toward Unified Remote Sensing Vector Mapping

Yinglong Yan, Yunkai Yang, Haoyi Wang, Wei Fu, Linshan Wu, Honghu Pan, Shaobo Xia, Shanghang Zhang, Hao Chen, Leyuan Fang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026 · 1-18

DOI: 10.1109/tpami.2026.3752281 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026. Verfasst von Yinglong Yan und 9 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Remote sensing vector mapping aims to generate structured maps of geospatial entities, such as buildings, roads, and water bodies, from remote sensing imagery. In practice, vector maps usually contain multiple category layers and heterogeneous entity structures, requiring a unified model for diverse mapping needs. However, existing methods typically represent vector objects as polygons or graphs, making them suitable only for specific categories: polygons poorly capture topological relations, while graphs often blur instance boundaries. We observe that language, as a natural medium for human communication, offers a flexible and expressive representation that can accommodate heterogeneous map elements, including geometry, semantics, and topology. Motivated by this insight, we propose Vector Map as Language (VecLang), a unified paradigm that reformulates multiclass vector mapping as structured text generation. VecLang encodes the common elements of different geospatial entities into a GeoJSON-like vector language, enabling cross-category modeling within a shared textual format. To generate this language reliably, we design a progressive vision-language mapping framework that first localizes vectorization units and then generates structured map elements. We further introduce Hierarchical Vector Language Optimization, which uses reinforcement learning to improve syntax validity, content fidelity, and map executability. We also build VecMap with 46k images and 800K instances, supporting training and evaluation across standard and generalization settings. Extensive experiments demonstrate that VecLang handles both single-class and multiclass vector mapping while achieving strong cross-dataset and open-vocabulary generalization.

Zitieren

APA

Yan, Y., Yang, Y., Wang, H., Fu, W., Wu, L., Pan, H., Xia, S., Zhang, S., Chen, H., & Fang, L. (2026). Vector Map as Language: Toward Unified Remote Sensing Vector Mapping. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1-18. https://doi.org/10.1109/tpami.2026.3752281

Vancouver

Yan Y, Yang Y, Wang H, Fu W, Wu L, Pan H, et al. Vector Map as Language: Toward Unified Remote Sensing Vector Mapping. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026:1-18. doi:10.1109/tpami.2026.3752281

BibTeX
@article{Yan2026,
  author = {Yan, Yinglong and Yang, Yunkai and Wang, Haoyi and Fu, Wei and Wu, Linshan and Pan, Honghu and Xia, Shaobo and Zhang, Shanghang and Chen, Hao and Fang, Leyuan},
  title = {Vector Map as Language: Toward Unified Remote Sensing Vector Mapping},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  pages = {1--18},
  doi = {10.1109/tpami.2026.3752281}
}
Kostenlos starten →