ObjectFusion: Multi-modal 3D object detection with object-centric fusion

• Main Authors: CAI, Q., PAN, Y., YAO, T., NGO, Chong-wah, MEI, T.
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: 3D object detection; Multi-modal; Fusion-based approach; Artificial Intelligence and Robotics; Robotics
• Online Access: https://ink.library.smu.edu.sg/sis_research/8306; https://ink.library.smu.edu.sg/context/sis_research/article/9309/viewcontent/Cai_ObjectFusion_Multi_modal_3D_Object_Detection_with_Object_Centric_Fusion_ICCV_2023_paper.pdf
• Institution: Singapore Management University

Recent progress on multi-modal 3D object detection has featured BEV (Bird-Eye-View) based fusion, which effectively unifies both LiDAR point clouds and camera images in a shared BEV space. Nevertheless, it is not trivial to perform camera-to-BEV transformation due to the inherently ambiguous depth e...