WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural Language

no code implementations • 12 Apr 2023 • Zhenxiang Lin, Xidong Peng, Peishan Cong, Yuenan Hou, Xinge Zhu, Sibei Yang, Yuexin Ma

We introduce the task of 3D visual grounding in large-scale dynamic scenes based on natural linguistic descriptions and online captured multi-modal visual data, including 2D images and 3D LiDAR point clouds.

Autonomous Driving Object Localization +1