Projecting your view attentively: Monocular road scene layout estimation via cross-view transformation

• Main Authors: YANG, Weixiang, LI, Qi, LIU, Wenxi, YU, Yuanlong, MA, Yuexin, HE, Shengfeng, PAN, Jia
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: Computer vision; Roads and streets; Vehicles; Autonomous driving; Bird's eye view; Camera-based; Local map; Map reconstruction; Road layouts; Road segmentation; Road vehicles; Vehicle occupancies; View transformations; Artificial Intelligence and Robotics; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/8440; https://ink.library.smu.edu.sg/context/sis_research/article/9443/viewcontent/Yang_Projecting_Your_View_Attentively_Monocular_Road_Scene_Layout_Estimation_via_CVPR_2021_paper.pdf
• Institution: Singapore Management University

HD map reconstruction is crucial for autonomous driving. LiDAR-based methods are limited due to the deployed expensive sensors and time-consuming computation. Camera-based methods usually need to separately perform road segmentation and view transformation, which often causes distortion and the abse...