DehazeNet: An End-to-End System for Single Image Haze Removal

DOI10.1109/TIP.2016.2598681MaRDI QIDQ4616795zbMATH OpenDBLPWikidataFDO

Authors Bolun Cai, Xiangmin Xu, Kui Jia, Chunmei Qing, Dacheng Tao

Publication date 4 February 2019

Published in IEEE Transactions on Image Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1601.07661

Mathematics Subject Classification ID

Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Abstract: Single image haze removal is a challenging ill-posed problem. Existing methods use various constraints/priors to get plausible dehazing solutions. The key to achieve haze removal is to estimate a medium transmission map for an input hazy image. In this paper, we propose a trainable end-to-end system called DehazeNet, for medium transmission estimation. DehazeNet takes a hazy image as input, and outputs its medium transmission map that is subsequently used to recover a haze-free image via atmospheric scattering model. DehazeNet adopts Convolutional Neural Networks (CNN) based deep architecture, whose layers are specially designed to embody the established assumptions/priors in image dehazing. Specifically, layers of Maxout units are used for feature extraction, which can generate almost all haze-relevant features. We also propose a novel nonlinear activation function in DehazeNet, called Bilateral Rectified Linear Unit (BReLU), which is able to improve the quality of recovered haze-free image. We establish connections between components of the proposed DehazeNet and those used in existing methods. Experiments on benchmark images show that DehazeNet achieves superior performance over existing methods, yet keeps efficient and easy to use.

Cited in

(15)

• DehazeNet
• Image restoration by learning morphological opening-closing network
• A probabilistic approach to restore images acquired in underwater scenes
• Simultaneous deep stereo matching and dehazing with feature attention
• Single image desmogging using oblique gradient profile prior and variational minimization
• A novel total generalized variation model for image dehazing
• Color image dehazing using gradient channel prior and guided L₀ filter
• Variational formulation of dark channel prior for single image dehazing
• AIPNet: Image-to-Image Single Image Dehazing With Atmospheric Illumination Prior
• FAMED-Net: A Fast and Accurate Multi-Scale End-to-End Dehazing Network
• Effective edge-aware weighting filter-based structural patch decomposition multi-exposure image fusion for single image dehazing
• Single image dehazing based on dynamic convolution and transformer
• An adaptive nonuniform map re-weighting method for image dehazing
• Variational image dehazing with a novel underwater dark channel prior
• A convex single image dehazing model via sparse dark channel prior

Describes a project that uses

Uses Software

• PCANet

This page was built for publication: DehazeNet: An End-to-End System for Single Image Haze Removal

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4616795)