Haze transfer and feature aggregation network for real-world single image dehazing

作者：

Highlights：

• We propose a haze transfer model for haze information from a real hazy image to a clear image.

• We develop a feature aggregation network to highlight the information related to clean images.

• The proposed method overcomes the drawback that the model cannot be applied to real hazy images.

摘要

•We propose a haze transfer model for haze information from a real hazy image to a clear image.•We develop a feature aggregation network to highlight the information related to clean images.•The proposed method overcomes the drawback that the model cannot be applied to real hazy images.

论文关键词：Image dehazing,Haze transfer,Feature aggregation,Chunking discrimination

论文评审过程：Received 1 December 2021, Revised 20 June 2022, Accepted 20 June 2022, Available online 26 June 2022, Version of Record 4 July 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.109309