Compensation Atmospheric Scattering Model and Two-Branch Network for Single Image Dehazing
- 18 April 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 8 (4) , 2880-2896
Abstract
Most existing dehazing networks rely on synthetic hazy-clear image pairs for training, and thus fail to work well in real-world scenes. In this paper, we deduce a reformulated atmospheric scattering model for a hazy image and propose a novel lightweight two-branch dehazing network. In the model, we use a Transformation Map to represent the dehazing transformation and use a Compensation Map to represent variable illumination compensation. Based on this model, we design a T wo- B ranch N etwork (TBN) to jointly estimate the Transformation Map and Compensation Map. Our TBN is designed with a shared Feature Extraction Module and two Adaptive Weight Modules. The Feature Extraction Module is used to extract shared features from hazy images. The two Adaptive Weight Modules generate two groups of adaptive weighted features for the Transformation Map and Compensation Map, respectively. This design allows for a targeted conversion of features to the Transformation Map and Compensation Map. To further improve the dehazing performance in the real-world, we propose a semi-supervised learning strategy for TBN. Specifically, by performing supervised pre-training based on synthetic image pairs, we propose a Self-Enhancement method to generate pseudo-labels, and then further train our TBN with the pseudo-labels in a semi-supervised way. Extensive experiments demonstrate that the model-based TBN outperforms the state-of-the-art methods on various real-world datasets.Keywords
Funding Information
- National Natural Science Foundation of China (U23A20343, 61873259, 61821005, 62206075)
- Liaoning Provincial (2023JH1/10400045)
- Guangdong Basic and Applied Basic Research Foundation (2021A1515110438)
- CAS
- Young Scientists in Basic Research (YSBR-041)
- Youth Innovation Promotion Association of the Chinese Academy of Sciences (Y202051, 2022196)
This publication has 80 references indexed in Scilit:
- AGLC-GAN: Attention-based global-local cycle-consistent generative adversarial networks for unpaired single image dehazingImage and Vision Computing, 2023
- Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning2022
- A Comprehensive Review on Analysis and Implementation of Recent Image Dehazing MethodsArchives of Computational Methods in Engineering, 2022
- Single image dehazing using improved cycleGANJournal of Visual Communication and Image Representation, 2021
- Single image dehazing by approximating and eliminating the additional airlight componentNeurocomputing, 2020
- DD-CycleGAN: Unpaired image dehazing via Double-Discriminator Cycle-Consistent Generative Adversarial NetworkEngineering Applications of Artificial Intelligence, 2019
- I-HAZE: A Dehazing Benchmark with Real Hazy and Haze-Free Indoor Images2018
- HDP-Net: Haze Density Prediction Network for Nighttime Dehazing2018
- Single image haze removal based on the improved atmospheric scattering modelNeurocomputing, 2017
- Single Image Dehazing via Multi-scale Convolutional Neural Networks2016