AI Paper Atlas

Research map / Point clouds / Point cloud classification

VLM-Loc: Localization in Point Cloud Maps via Vision-Language Models

Shuhao Kang, Youqi Liao, Peijie Wang, Wenlong Liao, Qilin Zhang, Benjamin Busam, Xieyuanli Chen, Yun Liu

CVPR 2026 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add partial node assignment (PNA) on top of scene graph (ablation)VLM-Loc · CityLoc-K testRecall@5m: 24.62 -> 32.34Improved
add PNA to BEV + scene graph (ablation)VLM-Loc · CityLoc-K testRecall@5m: 29.79 -> 35.91Improved
add scene graph input to BEV-only input (ablation)VLM-Loc · CityLoc-K testRecall@5m: 13.21 -> 29.79Improved
add BEV image to scene-graph-only input (ablation)VLM-Loc · CityLoc-K testRecall@5m: 24.62 -> 29.79Improved
use partial instead of full node assignment (ablation)VLM-Loc · CityLoc-K testRecall@5m: 17.81 -> 35.91Improved
add directional cues to text query (ablation)VLM-Loc · CityLoc-K testRecall@5m: 18.01 -> 35.91Improved
add color cues to text query (with direction) (ablation)VLM-Loc · CityLoc-K testRecall@5m: 16.93 -> 18.01 (without direction)No clear effect
scale backbone from Qwen3-VL-8B to 32B (ablation)VLM-Loc · CityLoc-K testRecall@5m: 35.91 -> 41.05Improved
scale backbone from Qwen3-VL-2B to 8B (ablation)VLM-Loc · CityLoc-K testRecall@5m: 34.70 -> 35.91No clear effect
replace CMMLoc with VLM-LocT2P localization · CityLoc-K testRecall@5m: 21.71 -> 35.91Improved
transfer VLM-Loc to unseen CityLoc-CT2P localization · CityLoc-CRecall@5m: 13.68 (MNCL) -> 21.37Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy