Retrieve-to-Localize: Bridging Large Language Models and LiDAR Geometry for Spatial Grounding

原文：Retrieve-to-Localize: Bridging Large Language Models and LiDAR Geometry for Spatial Grounding

作者：Byounggun Park, Giyong Moon, Jusung Kim, Soonmin Hwang

来源：arXiv cs.CV（计算机视觉）

正文

Computer Science > Computer Vision and Pattern Recognition

arXiv:2609.29835v1 (cs)

[Submitted on 24 Sep 2026]

Title:Retrieve-to-Localize: Bridging Large Language Models and LiDAR Geometry for Spatial Grounding

Authors:Byounggun Park, Giyong Moon, Jusung Kim, Soonmin Hwang

View a PDF of the paper titled Retrieve-to-Localize: Bridging Large Language Models and LiDAR Geometry for Spatial Grounding, by Byounggun Park and 2 other authors

View PDF

HTML (experimental)

Abstract:LiDAR provides precise geometric information for spatial perception tasks such as object detection in autonomous driving and outdoor robotics. However, recognizing and localizing individual objects is not sufficient to answer questions that require composing spatial relations and grounding the intended target. Motivated by recent advances in large language models (LLMs) for autonomous driving, we leverage their language priors to interpret complex spatial questions and ground the referred target in LiDAR geometry. To support this spatial grounding capability, we introduce SpatialLiDAR-QA, which combines single- and multi-step relational grounding with complementary spatial understanding tasks. We further propose SpatialLiDAR-LM, which aligns LiDAR point features with an LLM and grounds target coordinates through language-conditioned, position-aware proposal retrieval and local point refinement. This design derives target coordinates directly from local LiDAR geometry rather than through textual language decoding. Experiments demonstrate substantial improvements over representative LiDAR–language models and multi-camera VLMs on precise coordinate prediction tasks. Our dataset and model training code will be publicly released.

Comments:

8 pages

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)

Cite as:

arXiv:2609.29835 [cs.CV]

(or

arXiv:2609.29835v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2609.29835

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

计算机视觉 · 机器人

由「前沿雷达」于 2026-09-24 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。