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

ICLR2025顶会

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

问 Lune

摘要

This is a building that has brown multitiered roof sections, situated at the intersection point of two road named Walsall road and Regina Drive. The building has a large parking area.

问 Lune

尽管问，回答会引用原文。

Lune 会读完全文和相关的 Paper，每个回答都附上所依据的原文段落。

核心论断
谁在沿用
横向对比
局限

你的问题

Lune 的依据

全文 · 引用它的 2 篇顶会 Paper · 相关的 Paper

获取答案

免费开始，无需绑卡

引用它的顶会 Paper2

Why LVLMs are More Prone to Hallucinations in Longer Responses: The Role of ContextGe Zheng, Jiaye Qian, Jiajin Tang, Sibei YangICCV 2025 · 2 次引用
Partially Matching Submap Helps: Uncertainty Modeling and Propagation for Text to Point Cloud LocalizationMingtao Feng, Longlong Mei, Zijie Wu, Jianqiao Luo 等ICCV 2025 · 2 次引用

问问它们各自怎么用它

它引用的 Paper21

Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 47,906 次引用
Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao 等ICCV 2023 · 13,211 次引用
NExT-GPT: Any-to-Any Multimodal LLMShengqiong Wu, Hao Fei, Leigang Qu, Wei Ji 等ICML 2024 · 786 次引用
3D-LLM: Injecting the 3D World into Large Language ModelsYining Hong, Haoyu Zhen, Peihao Chen, Shuhong Zheng 等NeurIPS 2023 · 662 次引用
SoftGroup for 3D Instance Segmentation on Point CloudsThang Vu, Kookhoi Kim, Tung Minh Luu, Thanh Xuan Nguyen 等CVPR 2022 · 251 次引用

摘要

问 Lune

尽管问，回答会引用原文。

引用它的顶会 Paper2

它引用的 Paper21

相关 Paper