A Novel Transformer-Based Attention Network for Image Dehazing

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 e...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Switzerland), 2022-04, Vol.22 (9), p.3428
Main Authors: Gao, Guanlei, Cao, Jie, Bao, Chun, Hao, Qun, Ma, Aoqi, Li, Gang
Format: Article
Language:English
Subjects:
Ablation
Computational linguistics
convolutional neural network
image dehazing
Image quality
Language processing
Light
Methods
Natural language interfaces
Neural networks
Parameter estimation
Remote sensing
Transformer
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1424-8220
1424-8220
DOI:10.3390/s22093428