Underwater image enhancement with global–local networks and compressed-histogram equalization

作者：

Highlights：

• The proposed method integrates deep learning and handcrafted image enhancement.

• The proposed method has a lightweight architecture for underwater image enhancement.

• The proposed method improves image contrast without over-enhancement.

• The proposed method has a lightweight architecture and efficient computation time.

摘要

•The proposed method integrates deep learning and handcrafted image enhancement.•The proposed method has a lightweight architecture for underwater image enhancement.•The proposed method improves image contrast without over-enhancement.•The proposed method has a lightweight architecture and efficient computation time.

论文关键词：Underwater image,Deep learning,Image enhancement,CNNs

论文评审过程：Received 16 January 2020, Revised 29 March 2020, Accepted 27 May 2020, Available online 30 May 2020, Version of Record 2 June 2020.

论文官网地址：https://doi.org/10.1016/j.image.2020.115892