Cargando…

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Gao, Guanlei, Cao, Jie, Bao, Chun, Hao, Qun, Ma, Aoqi, Li, Gang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9105677/
https://www.ncbi.nlm.nih.gov/pubmed/35591118
http://dx.doi.org/10.3390/s22093428
_version_ 1784708099080192000
author Gao, Guanlei
Cao, Jie
Bao, Chun
Hao, Qun
Ma, Aoqi
Li, Gang
author_facet Gao, Guanlei
Cao, Jie
Bao, Chun
Hao, Qun
Ma, Aoqi
Li, Gang
author_sort Gao, Guanlei
collection PubMed
description 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.
format Online
Article
Text
id pubmed-9105677
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-91056772022-05-14 A Novel Transformer-Based Attention Network for Image Dehazing Gao, Guanlei Cao, Jie Bao, Chun Hao, Qun Ma, Aoqi Li, Gang Sensors (Basel) Article 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. MDPI 2022-04-30 /pmc/articles/PMC9105677/ /pubmed/35591118 http://dx.doi.org/10.3390/s22093428 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Gao, Guanlei
Cao, Jie
Bao, Chun
Hao, Qun
Ma, Aoqi
Li, Gang
A Novel Transformer-Based Attention Network for Image Dehazing
title A Novel Transformer-Based Attention Network for Image Dehazing
title_full A Novel Transformer-Based Attention Network for Image Dehazing
title_fullStr A Novel Transformer-Based Attention Network for Image Dehazing
title_full_unstemmed A Novel Transformer-Based Attention Network for Image Dehazing
title_short A Novel Transformer-Based Attention Network for Image Dehazing
title_sort novel transformer-based attention network for image dehazing
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9105677/
https://www.ncbi.nlm.nih.gov/pubmed/35591118
http://dx.doi.org/10.3390/s22093428
work_keys_str_mv AT gaoguanlei anoveltransformerbasedattentionnetworkforimagedehazing
AT caojie anoveltransformerbasedattentionnetworkforimagedehazing
AT baochun anoveltransformerbasedattentionnetworkforimagedehazing
AT haoqun anoveltransformerbasedattentionnetworkforimagedehazing
AT maaoqi anoveltransformerbasedattentionnetworkforimagedehazing
AT ligang anoveltransformerbasedattentionnetworkforimagedehazing
AT gaoguanlei noveltransformerbasedattentionnetworkforimagedehazing
AT caojie noveltransformerbasedattentionnetworkforimagedehazing
AT baochun noveltransformerbasedattentionnetworkforimagedehazing
AT haoqun noveltransformerbasedattentionnetworkforimagedehazing
AT maaoqi noveltransformerbasedattentionnetworkforimagedehazing
AT ligang noveltransformerbasedattentionnetworkforimagedehazing