Lightweight multi-scale convolutional neural network for real time stereo matching

作者：

Highlights：

• The proposed LMNet can balance time efficiency and matching accuracy.

• Lightweight MS2D module can extract more global features with less computation.

• Lightweight MS3D module yield roubust results especially for slim objects.

摘要

•The proposed LMNet can balance time efficiency and matching accuracy.•Lightweight MS2D module can extract more global features with less computation.•Lightweight MS3D module yield roubust results especially for slim objects.

论文关键词：Stereo matching,Multi-scale,Refinement,Lightweight

论文评审过程：Received 15 January 2022, Revised 22 May 2022, Accepted 9 June 2022, Available online 15 June 2022, Version of Record 20 June 2022.

论文官网地址：https://doi.org/10.1016/j.imavis.2022.104510