FloodNet: Underwater image restoration based on residual dense learning
作者：
Highlights：
• Propose FloodNet, an end-to-end CNN architecture to restored underwater images from a wide variety of degraded underwater images.
• Introduce residual dense blocks to connect the convolutional layers using skip-connections.
• Global feature fusion to adaptively utilize both local and global residual learning.
• Exhaustive perspective and quantitative experimental analysis on paired and unpaired underwater images.
• Perform application and user study analysis.
摘要
•Propose FloodNet, an end-to-end CNN architecture to restored underwater images from a wide variety of degraded underwater images.•Introduce residual dense blocks to connect the convolutional layers using skip-connections.•Global feature fusion to adaptively utilize both local and global residual learning.•Exhaustive perspective and quantitative experimental analysis on paired and unpaired underwater images.•Perform application and user study analysis.
论文关键词：Underwater image restoration,Residual dense block,Global feature fusion,Convolutional neural network,UIEB dataset
论文评审过程：Received 18 December 2020, Revised 15 December 2021, Accepted 17 January 2022, Available online 7 February 2022, Version of Record 24 February 2022.
论文官网地址：https://doi.org/10.1016/j.image.2022.116647
