A Comprehensive Survey and Taxonomy on Image Dehazing Based on Deep Learning
Authors:
- Xiaofeng CongXCXiaofeng Cong
- Yuan CaoYCYuan Cao
- Wenqi RenWRWenqi Ren
- Jun ZhangJZJun Zhang
- Jing ZhangJZJing Zhang
- Jiuxin CaoJCJiuxin Cao
- Dacheng TaoDTDacheng Tao
Preprint
Abstract
With the development of convolutional neural networks, hundreds of deep learning based dehazing methods have been proposed. In this paper, we provide a comprehensive survey on supervised, semi-supervised, and unsupervised dehazing. We first discuss the physical model, datasets, network modules, loss functions, and evaluation metrics that are commonly used. Then, the main contributions of various dehazing algorithms are categorized and summarized. Further, quantitative and qualitative experiments of various baseline methods are carried out. Finally, the unsolved issues and challenges that can inspire the future research are pointed out. A collection of useful dehazing materials is available at https://github.com/Xiaofeng-life/AwesomeDehazing.Keywords
All Related Versions
This publication has 81 references indexed in Scilit:
- An ensemble multi-scale residual attention network (EMRA-net) for image DehazingMultimedia Tools and Applications, 2021
- A guiding teaching and dual adversarial learning framework for a single image dehazingThe Visual Computer, 2021
- Depth aware image dehazingThe Visual Computer, 2021
- You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural NetworkInternational Journal of Computer Vision, 2021
- Pyramid Channel-based Feature Attention Network for image dehazingComputer Vision and Image Understanding, 2020
- DRCDN: learning deep residual convolutional dehazing networksThe Visual Computer, 2019
- Joint learning of image detail and transmission map for single image dehazingThe Visual Computer, 2018
- A Comprehensive Review of Computational Dehazing TechniquesArchives of Computational Methods in Engineering, 2018
- Haze visibility enhancement: A Survey and quantitative benchmarkingComputer Vision and Image Understanding, 2017
- The CIEDE2000 color-difference formula: Implementation notes, supplementary test data, and mathematical observationsColor Research & Application, 2004