GMS: Grid-Based Motion Statistics for Fast, Ultra-Robust Feature Correspondence

Bian, Jia-Wang; Lin, Wen-Yan; Matsushita, Yasuyuki; Yeung, Sai-Kit; Nguyen, Tan-Dat; Cheng, Ming‐Ming

doi:10.1109/cvpr.2017.302

Public

GMS: Grid-Based Motion Statistics for Fast, Ultra-Robust Feature Correspondence

Published • Jul 1, 2017

Authors:

Jia-Wang Bian

Wen-Yan Lin

Yasuyuki Matsushita

Abstract

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 smo...

Subject

Computer science

Feature matching

Feature (linguistics)

Research Assistant

AI chat, annotations, notes & similar papers

Finding related papers...

Discussions

(0)

No comments yet

Be the first to share your thoughts!