Metraipolis › archive › dc_ff6423d8dc0c
How to Reduce Localization Ambiguity? Geometry-Semantic Constrained BEV Representation Learning for Satellite-Ground Localization — arXiv:2609.39127
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39127
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T14:45:51.779Z
- SHA-256 of the archived text
2bcc27e21729014a9349edd1feac64940c34565ec5a174fc61123c258a30c8c4- Stable URL of this page
https://metraipolis.com/documento/dc_ff6423d8dc0c
How to cite
How to Reduce Localization Ambiguity? Geometry-Semantic Constrained BEV Representation Learning for Satellite-Ground Localization — arXiv:2609.39127 — arXiv (en), https://arxiv.org/abs/2609.39127 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff6423d8dc0c (Metraipolis archive dc_ff6423d8dc0c, sha256 2bcc27e21729014a9349edd1feac64940c34565ec5a174fc61123c258a30c8c4)
BibTeX
@misc{dcff6423d8dc0c,
title = {How to Reduce Localization Ambiguity? Geometry-Semantic Constrained BEV Representation Learning for Satellite-Ground Localization — arXiv:2609.39127},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39127},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff6423d8dc0c; sha256 2bcc27e21729014a9349edd1feac64940c34565ec5a174fc61123c258a30c8c4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39127. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Satellite-ground localization estimates the planar position and yaw orientation of a ground camera within a geo-referenced satellite image. Most recent methods map ground and satellite features into a shared bird's-eye-view (BEV) space and establish spatial correspondences. However, insufficient depth constraints can assign one ground feature to different distances along a viewing direction, creating geometric ambiguity in BEV feature placement. Similar appearances at different locations can also create descriptor matching ambiguity, while existing descriptor learning lacks explicit semantic supervision to distinguish them. We propose GeoSem-BEV, a geometry-semantic constrained BEV representation learning method. Radial depth supervision constrains distance assignment, and vertical height supervision constrains height aggregation. Shared explicit semantic supervision promotes consistent semantic predictions across views and helps distinguish locations with similar semantics. These constraints improve feature placement and descriptor discriminability, enhancing state-of-the-art BEV localization models. On VIGOR with unknown orientation, GeoSem-BEV reduces mean orientation error by 37.2% and 38.1% in the cross-area and same-area settings, respectively. The corresponding errors are reduced by 10.8% and 15.6% on DReSS-D. On KITTI-CVL, it reduces same-area mean orientation error by 26.8% under 10 degree orientation noise. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.39127 — 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 2026-10-07T14:19:00.679Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).