点击次数：

论文类型：会议论文

发表时间：2017-01-01

收录刊物：CPCI-S

页面范围：795-799

关键字：Deep feature; dense correspondence; scene matching; optical flow; handcrafted feature

摘要：Image matching is a challenging problem as different views often undergo significant appearance changes caused by deformation, abrupt motion, and occlusion. In this paper, we explore features extracted from convolutional neural networks to help the estimation of image matching so that dense pixel correspondence can be built. As the deep features are able to describe the image structures, the matching method based on these features is able to match across different scenes and/or object appearances. We analyze the deep features and compare them with other robust features, e.g., SIFT. Extensive experiments on 5 datasets demonstrate the proposed algorithm performs favorably against the state-of-the-art methods in terms of visually matching quality and accuracy.