Metraipolis › archive › dc_389bb0d37bdf

Aerial Content-Aware Sample-Adaptive Classifier for Urban Photogrammetric Point Cloud Segmentation — arXiv:2611.02844

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02844
License (as archived)
CC0-1.0
Archived
2026-11-03T11:42:39.491Z
SHA-256 of the archived text
f5b0ad98d3f61a47346941c66ad725efc8f0557835aa1ae1fa192eb40f3d7f70
Stable URL of this page
https://metraipolis.com/documento/dc_389bb0d37bdf

How to cite

Aerial Content-Aware Sample-Adaptive Classifier for Urban Photogrammetric Point Cloud Segmentation — arXiv:2611.02844 — arXiv (en), https://arxiv.org/abs/2611.02844 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_389bb0d37bdf (Metraipolis archive dc_389bb0d37bdf, sha256 f5b0ad98d3f61a47346941c66ad725efc8f0557835aa1ae1fa192eb40f3d7f70)
BibTeX
@misc{dc389bb0d37bdf,
  title = {Aerial Content-Aware Sample-Adaptive Classifier for Urban Photogrammetric Point Cloud Segmentation — arXiv:2611.02844},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02844},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_389bb0d37bdf; sha256 f5b0ad98d3f61a47346941c66ad725efc8f0557835aa1ae1fa192eb40f3d7f70},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02844. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Urban photogrammetric point clouds are commonly processed as local 3D patches, limiting the context available for distinguishing geometrically similar categories. Orthographic projection of the same data yields a co-registered digital orthophoto map (DOM)/RGB-D representation that supports efficient large-context modeling but compresses vertical geometry. Existing projection--point methods mainly fuse these two representations at the feature level while retaining a classifier shared across all samples. We present the Aerial Content-Aware Sample-Adaptive Classifier (ACASAC), which complements feature fusion with decision-level adaptation. A point-aligned aerial region bridges the full aerial crop and local 3D patch. ACASAC models scene-to-local variation within the projection and the representation discrepancy between aligned 2D and 3D supports, then transfers both relations to refine the local point class representation. The refined representation, scene-level aerial context, and fixed fused-head prior jointly form a classifier for the current sample. ACASAC improves the fixed dual-representation head by 2.1 and 2.7 mIoU points on SensatUrban and UrbanBIS, respectively, and by 2.1--2.3 points across four tested encoder combinations.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.02844 — 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 2026-11-03T11:06:37.594Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).