arXiv：cs.CL· Shengkai Ma, Zhenyu Hou, Weihua Cao·· 3 小时前AI 评分38
PARC-Loc：用部分分配与关系一致性实现文本到点云定位
PARC-Loc: Text-to-Point-Cloud Localization with Partial Assignment and Relational Consistency
AI 导读
研究提出 PARC-Loc 文本到点云定位框架，通过部分分配与关系一致性（PARC）联合建模提示物体兼容性与成对空间关系，在粗阶段补充神经相似度做布局一致的子图选择，细阶段用相邻子图扩展上下文。在 KITTI360Pose 上，5 米内 Top-1 定位召回率从 0.50 提升至 0.67，相对最强基线提升 34%，并在 CityLoc 上同样优于传统由粗到细基线。
正文
Abstract: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.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.09761 [cs.CV] |
| (or arXiv:2610.09761v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09761 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shengkai Ma [view email]
[v1]
Wed, 7 Oct 2026 09:46:34 UTC (2,312 KB)
来源：arXiv：cs.CL · arxiv.org