» Articles » PMID: 35591118

A Novel Transformer-Based Attention Network for Image Dehazing

Overview
Journal Sensors (Basel)
Publisher MDPI
Specialty Biotechnology
Date 2022 May 20
PMID 35591118
Authors
Affiliations
Soon will be listed here.
Abstract

Image dehazing is challenging due to the problem of ill-posed parameter estimation. Numerous prior-based and learning-based methods have achieved great success. However, most learning-based methods use the changes and connections between scale and depth in convolutional neural networks for feature extraction. Although the performance is greatly improved compared with the prior-based methods, the performance in extracting detailed information is inferior. In this paper, we proposed an image dehazing model built with a convolutional neural network and Transformer, called Transformer for image dehazing (TID). First, we propose a Transformer-based channel attention module (TCAM), using a spatial attention module as its supplement. These two modules form an attention module that enhances channel and spatial features. Second, we use a multiscale parallel residual network as the backbone, which can extract feature information of different scales to achieve feature fusion. We experimented on the RESIDE dataset, and then conducted extensive comparisons and ablation studies with state-of-the-art methods. Experimental results show that our proposed method effectively improves the quality of the restored image, and it is also better than the existing attention modules in performance.

Citing Articles

An Image Dehazing Algorithm for Underground Coal Mines Based on gUNet.

Tian F, Gao L, Zhang J Sensors (Basel). 2024; 24(11).

PMID: 38894221 PMC: 11174353. DOI: 10.3390/s24113422.


Vision Transformers in Image Restoration: A Survey.

M Ali A, Benjdira B, Koubaa A, El-Shafai W, Khan Z, Boulila W Sensors (Basel). 2023; 23(5).

PMID: 36904589 PMC: 10006889. DOI: 10.3390/s23052385.


Insulator Umbrella Disc Shedding Detection in Foggy Weather.

Xin R, Chen X, Wu J, Yang K, Wang X, Zhai Y Sensors (Basel). 2022; 22(13).

PMID: 35808378 PMC: 9269560. DOI: 10.3390/s22134871.

References
1.
Kim J, Sim J, Kim C . Video deraining and desnowing using temporal correlation and low-rank matrix completion. IEEE Trans Image Process. 2015; 24(9):2658-70. DOI: 10.1109/TIP.2015.2428933. View

2.
Yeh C, Huang C, Kang L . Multi-Scale Deep Residual Learning-Based Single Image Haze Removal via Image Decomposition. IEEE Trans Image Process. 2019; . DOI: 10.1109/TIP.2019.2957929. View

3.
Wang Y, Liu S, Chen C, Zeng B . A Hierarchical Approach for Rain or Snow Removing in a Single Color Image. IEEE Trans Image Process. 2017; 26(8):3936-3950. DOI: 10.1109/TIP.2017.2708502. View

4.
Mahdaoui A, Ouahabi A, Moulay M . Image Denoising Using a Compressive Sensing Approach Based on Regularization Constraints. Sensors (Basel). 2022; 22(6). PMC: 8949665. DOI: 10.3390/s22062199. View

5.
Cai B, Xu X, Jia K, Qing C, Tao D . DehazeNet: An End-to-End System for Single Image Haze Removal. IEEE Trans Image Process. 2017; 25(11):5187-5198. DOI: 10.1109/TIP.2016.2598681. View