AI Paper Atlas

Research map / Point clouds / Point cloud classification

CityAnchor: City-scale 3D Visual Grounding with Multi-modality LLMs

Jinpeng Li, Haiping Wang, Jiabin chen, Yuan Liu, Zhiyang Dou, Yuexin Ma, Sibei Yang, Yuan Li, Wenping Wang, Zhen Dong, Bisheng Yang

ICLR 2025 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Presents CityAnchor, a method for localizing urban objects described in language within city-scale point clouds using multi-modality LLMs.

Problem

Visual grounding of urban objects in city-scale 3D point clouds, which prior 3D visual grounding systems (focused on indoor or single-scene settings) do not handle.

Approach

Localizes an object in a city-scale point cloud by using multi-modality LLMs to ground the target; the abstract only states the high-level approach, with details about the specific mechanism not available.

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