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

• Main Authors: BIAN, Jiawang, LIN, Wen-yan, YASUYUKI, Matsushita, YEUNG, Sai-Kit, NGUYEN, Tan-Dat, CHENG, Ming-Ming
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2017
• Subjects: Computer and Systems Architecture
• Online Access: https://ink.library.smu.edu.sg/sis_research/4805; https://ink.library.smu.edu.sg/context/sis_research/article/5808/viewcontent/Bian_GMS_Grid_based_Motion_CVPR_2017_paper.pdf
• Institution: Singapore Management University

Incorporating smoothness constraints into feature matching is known to enable ultra-robust matching. However, such formulations are both complex and slow, making them unsuitable for video applications. This paper proposes GMS (Grid-based Motion Statistics), a simple means of encapsulating motion smoothness as the statistical likelihood of a certain number of matches in a region. GMS enables translation of high match numbers into high match quality. This provides a real-time, ultra-robust correspondence system. Evaluation on videos, with low textures, blurs and wide-baselines show GMS consistently out-performs other real-time matchers and can achieve parity with more sophisticated, much slower techniques.