UIEC^2-Net: CNN-based underwater image enhancement using two color space

作者：

Highlights：

• An end-to-end CNN-based underwater image enhancement using RGB and HSV color space is proposed. We are the first to use HSV color space for underwater image enhancement based on deep learning.

• A piece-wise linear scaling curve is learned to adjust image properties in HSV color space.

• Using differentiable RGB and HSV color space conversions to permit the end-to-end learning.

• Our model has better generalization ability and gets better results on real-world underwater image datasets.

摘要

•An end-to-end CNN-based underwater image enhancement using RGB and HSV color space is proposed. We are the first to use HSV color space for underwater image enhancement based on deep learning.•A piece-wise linear scaling curve is learned to adjust image properties in HSV color space.•Using differentiable RGB and HSV color space conversions to permit the end-to-end learning.•Our model has better generalization ability and gets better results on real-world underwater image datasets.

论文关键词：Underwater image enhancement,HSV color space,Deep learning

论文评审过程：Received 31 July 2020, Revised 10 March 2021, Accepted 23 March 2021, Available online 16 April 2021, Version of Record 24 April 2021.

论文官网地址：https://doi.org/10.1016/j.image.2021.116250