GMS: Grid-based motion statistics for fast, ultra-robust feature correspondence

• Main Authors: BIAN, Jia-Wang, LIN, Wen-yan, LIU, Yun, ZHANG, Le, YEUNG, Sai-Kit, CHENG, Ming-Ming, REID, Ian
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2019
• Subjects: Feature matching; Epipolar geometry; Visual SLAM; Structure-from-motion; GMS; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/5877; https://ink.library.smu.edu.sg/context/sis_research/article/6892/viewcontent/Bian2020_Article_GMSGrid_BasedMotionStatisticsF__1_.pdf
• Institution: Singapore Management University

Feature matching aims at generating correspondences across images, which is widely used in many computer vision tasks. Although considerable progress has been made on feature descriptors and fast matching for initial correspondence hypotheses, selecting good ones from them is still challenging and c...