AgentGrounder: Zero-Shot 3D Visual Pointcloud Grounding using Multimodal Language Models 文章

ArXiv CS.CV2026-05-26NEWSen作者: Cuong Huynh, Maxim Popov, Denis Gridusov, Sergey Kolyubin
查看原文 →
关系图谱

AgentGrounder: Zero-Shot 3D Visual Pointcloud Grounding using Multimodal Language Models · 相关技术

相关技术

Object Lookup TableLVLMs3D Visual Grounding