Attention-guided aggregation stereo matching network

作者：

Highlights：

• An attention-guided aggregation stereo matching network is proposed.

• The residual network based on the 2D channel attention block is proposed.

• The 3D stacked hourglass structure based on the 3D channel attention block is proposed.

• The 4D guided cost volume is designed.

摘要

•An attention-guided aggregation stereo matching network is proposed.•The residual network based on the 2D channel attention block is proposed.•The 3D stacked hourglass structure based on the 3D channel attention block is proposed.•The 4D guided cost volume is designed.

论文关键词：Convolutional neural network,Stereo matching,Attention mechanism,Guided cost volume

论文评审过程：Received 12 October 2020, Revised 30 November 2020, Accepted 3 December 2020, Available online 10 December 2020, Version of Record 23 December 2020.

论文官网地址：https://doi.org/10.1016/j.imavis.2020.104088