Visualizing the invisible: Occluded vehicle segmentation and recovery

• Main Authors: YAN, Xiaosheng, WANG, Feigege, LIU, Wenxi, YU, Yuanlong, HE, Shengfeng, PAN, Jia
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2019
• Subjects: Invisible parts; Real world videos; Recovery capabilities; Segmentation masks; Shared network; State of the art; Vehicle images; Vehicle segmentation; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/8522; https://ink.library.smu.edu.sg/context/sis_research/article/9525/viewcontent/Visualizing_the_Invisible__Occluded_Vehicle_Segmentation_and_Recovery.pdf
• Institution: Singapore Management University

In this paper, we propose a novel iterative multi-task framework to complete the segmentation mask of an occluded vehicle and recover the appearance of its invisible parts. In particular, firstly, to improve the quality of the segmentation completion, we present two coupled discriminators that intro...