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
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
- CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data (NeurIPS 2023 · similarity 0.90)
- Multi-View Transformer for 3D Visual Grounding (CVPR 2022 · similarity 0.89)
- Multi-Object 3D Grounding with Dynamic Modules and Language-Informed Spatial Attention (NeurIPS 2024 · similarity 0.86)
- From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes (NeurIPS 2025 · similarity 0.86)
- Point Transformer V3: Simpler Faster Stronger (CVPR 2024 · similarity 0.86)
- ProxyTransformation: Preshaping Point Cloud Manifold With Proxy Attention For 3D Visual Grounding (CVPR 2025 · similarity 0.86)
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.
