Metraipolis › archive › dc_312a91c49526
PARC-Loc: Text-to-Point-Cloud Localization with Partial Assignment and Relational Consistency — arXiv:2610.09761
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.09761
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T11:11:24.857Z
- SHA-256 of the archived text
7cdf617c06df2c2e10c6f47f301a7db88d3c8f7bc70454347be3cbee2725da52- Stable URL of this page
https://metraipolis.com/documento/dc_312a91c49526
How to cite
PARC-Loc: Text-to-Point-Cloud Localization with Partial Assignment and Relational Consistency — arXiv:2610.09761 — arXiv (en), https://arxiv.org/abs/2610.09761 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_312a91c49526 (Metraipolis archive dc_312a91c49526, sha256 7cdf617c06df2c2e10c6f47f301a7db88d3c8f7bc70454347be3cbee2725da52)
BibTeX
@misc{dc312a91c49526,
title = {PARC-Loc: Text-to-Point-Cloud Localization with Partial Assignment and Relational Consistency — arXiv:2610.09761},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.09761},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_312a91c49526; sha256 7cdf617c06df2c2e10c6f47f301a7db88d3c8f7bc70454347be3cbee2725da52},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09761. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Text-to-point-cloud localization estimates a position in a city-scale 3D map from descriptions of surrounding objects. Existing coarse-to-fine methods retrieve submaps using aggregate learned compatibility and then localize within a selected submap. However, repetitive or similar urban objects can inflate the embedding similarity between the query and multiple submaps, even when the instance layout within a submap violates the query description. Meanwhile, query-relevant instances often span submap boundaries, leaving the retrieved submap with incomplete contextual evidence. We term these failure modes layout-inconsistent aliasing and boundary evidence incompleteness, respectively. To address them, we propose PARC-Loc, a coarse-to-fine localization framework built on Partial Assignment with Relational Consistency (PARC). PARC jointly models hint-object compatibility and pairwise spatial relations, allowing unmatched elements while favoring assignments consistent with the queried layout. At the coarse stage, its candidate-level assessment complements neural similarity for layout-consistent submap selection. At the fine stage, the context is expanded with query-relevant instances from adjacent submaps, while PARC yields object-level matching weights that guide cross-modal attention. Extensive experiments on KITTI360Pose and CityLoc show that PARC-Loc outperforms conventional coarse-to-fine baselines. On KITTI360Pose, our method improves Top-1 localization recall at 5 m from 0.50 to 0.67, achieving a 34% relative gain over the strongest baseline. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.09761 — 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 2026-10-08T10:14:06.121Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).