Metraipolis › archive › dc_56fbb029fbbe

PolyTopoBench: A Benchmark for Complex Vector Polygon Generation from Remote Sensing Imagery — arXiv:2609.32856

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32856
License (as archived)
CC0-1.0
Archived
2026-10-07T21:00:41.977Z
SHA-256 of the archived text
1cc5b33a4db3e4fbc2447d3de02ff65e55622c69a3cd1884f3f7c5aef3af0a53
Stable URL of this page
https://metraipolis.com/documento/dc_56fbb029fbbe

How to cite

PolyTopoBench: A Benchmark for Complex Vector Polygon Generation from Remote Sensing Imagery — arXiv:2609.32856 — arXiv (en), https://arxiv.org/abs/2609.32856 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_56fbb029fbbe (Metraipolis archive dc_56fbb029fbbe, sha256 1cc5b33a4db3e4fbc2447d3de02ff65e55622c69a3cd1884f3f7c5aef3af0a53)
BibTeX
@misc{dc56fbb029fbbe,
  title = {PolyTopoBench: A Benchmark for Complex Vector Polygon Generation from Remote Sensing Imagery — arXiv:2609.32856},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32856},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_56fbb029fbbe; sha256 1cc5b33a4db3e4fbc2447d3de02ff65e55622c69a3cd1884f3f7c5aef3af0a53},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32856. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vector polygon generation converts visual inputs, e.g., remote sensing (RS) images, into vectorized polygonal geometries, supporting applications such as autonomous driving, vector map construction, and remote sensing. Early pipelines predict raster masks and post-process them into polygons, which prevents end-to-end optimization and may miss small objects or introduce inaccurate vertices. Recent methods directly generate vector polygons, but most focus on simple exterior contours, while they either cannot represent complex polygons with holes or fail to preserve their topology. In this paper, we propose PolyTopoBench, a unified evaluation framework for vector polygon generation from RS images with explicit emphasis on complex polygons. PolyTopoBench evaluates both exterior and interior rings, and benchmarks 11 representative methods, including segmentation-based polygonization pipelines, vision foundation model baselines, and specialized vector polygon generators, on two RS-image datasets covering buildings, roads, vegetation, and unvegetated regions. Experiments show that existing methods often recover simple exterior boundaries but degrade substantially on polygons with holes or multiple rings. These results reveal complex polygon generation as an unresolved challenge and motivate topology-aware benchmarks and model designs. Code and data are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.32856 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T20:29:02.479Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).