CSDA-Net: Seeking reliable correspondences by channel-Spatial difference augment network

作者：

Highlights：

• We propose an innovative network for feature matching.

• We introduce attention mechanism to extract global context information.

• We exploit the Overlay Attention block, to capture local and global context information.

• Experimental results show the proposed network is superior to state of the art networks.

摘要

•We propose an innovative network for feature matching.•We introduce attention mechanism to extract global context information.•We exploit the Overlay Attention block, to capture local and global context information.•Experimental results show the proposed network is superior to state of the art networks.

论文关键词：Feature matching,Deep learning,Outlier rejection,Attention mechanism

论文评审过程：Received 27 April 2021, Revised 26 November 2021, Accepted 14 January 2022, Available online 17 January 2022, Version of Record 1 February 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108539