A confidence prior for image dehazing

作者：

Highlights：

• We propose a unified framework for better explanation of several existing priors.

• Under the unified framework, we derive a confidence prior that uses a ratio to freely adjust the removal degree of outliers or noises.

• To solve heterogeneity of image signals and abrupt depth jumps in hazy images, we use a learning method to adaptively estimate a confidence ratio for each pixel.

摘要

•We propose a unified framework for better explanation of several existing priors.•Under the unified framework, we derive a confidence prior that uses a ratio to freely adjust the removal degree of outliers or noises.•To solve heterogeneity of image signals and abrupt depth jumps in hazy images, we use a learning method to adaptively estimate a confidence ratio for each pixel.

论文关键词：Regression,Classification,Image dehazing,Confidence prior,Appearance feature

论文评审过程：Received 6 July 2020, Revised 17 April 2021, Accepted 30 May 2021, Available online 22 June 2021, Version of Record 22 June 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108076