Metraipolis › archive › dc_a26feac475f4

Retrieve-to-Localize: Bridging Large Language Models and LiDAR Geometry for Spatial Grounding — arXiv:2609.29835

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29835
License (as archived)
CC0-1.0
Archived
2026-10-08T06:44:36.911Z
SHA-256 of the archived text
93a5bfebf62e6bf4191ac46865c512c4d978e50b7feefd3feaed0ea86f83ad8b
Stable URL of this page
https://metraipolis.com/documento/dc_a26feac475f4

How to cite

Retrieve-to-Localize: Bridging Large Language Models and LiDAR Geometry for Spatial Grounding — arXiv:2609.29835 — arXiv (en), https://arxiv.org/abs/2609.29835 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a26feac475f4 (Metraipolis archive dc_a26feac475f4, sha256 93a5bfebf62e6bf4191ac46865c512c4d978e50b7feefd3feaed0ea86f83ad8b)
BibTeX
@misc{dca26feac475f4,
  title = {Retrieve-to-Localize: Bridging Large Language Models and LiDAR Geometry for Spatial Grounding — arXiv:2609.29835},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29835},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a26feac475f4; sha256 93a5bfebf62e6bf4191ac46865c512c4d978e50b7feefd3feaed0ea86f83ad8b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29835. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.29835 — 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 2026-10-08T06:09:29.888Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).