Image dehazing based on double branch convolution and detail enhancement

Because of detail loss, color distortion and contrast reduction in the image dehazing process in a haze condition, we proposed the image dehazing network based on double branch convolution and detail enhancement, which consists of image dehazing module and detail enhancement module. First, in the im...

Full description

Saved in:
Bibliographic Details
Main Authors: ZHAI Fengwen, ZHU Yutong, JIN Jing
Format: Article
Language:zho
Published: EDP Sciences 2025-02-01
Series:Xibei Gongye Daxue Xuebao
Subjects:
Online Access:https://www.jnwpu.org/articles/jnwpu/full_html/2025/01/jnwpu2025431p109/jnwpu2025431p109.html
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850269547030904832
author ZHAI Fengwen
ZHU Yutong
JIN Jing
author_facet ZHAI Fengwen
ZHU Yutong
JIN Jing
author_sort ZHAI Fengwen
collection DOAJ
description Because of detail loss, color distortion and contrast reduction in the image dehazing process in a haze condition, we proposed the image dehazing network based on double branch convolution and detail enhancement, which consists of image dehazing module and detail enhancement module. First, in the image dehazing module, we designed a double branch convolutional block based on depth-separable convolution and differential convolution and then combined it with the U-Net network, effectively reducing the detail loss in the image dehazing process. In the image dehazing model, we introduced the attention module composed of channel attention mechanism and pixel attention mechanism, which improves its feature extraction ability, suppresses the features that are not related to the current task and further reduces the color distortion and contrast in the image dehazing process. Then, we input the image dehazed with the image dehazing module into the detail enhancement module to further recover image details, so that the image is more similar to that in its real domain. The combination of the image dehazing module with the detail enhancement module improves the generalization ability of the image dehazing network and makes it more adaptable to the haze dataset. We carried out experiments with the public datasets ITS and Haze4K and the public real dataset IHAZE. The quantitative objective analysis and comparison show that the peak signal-to-noise ratio and the structural similarity index reach 39.69 dB and 0.994 respectively, indicating that there is a certain improvement compared with the optimal algorithm in the comparison network model. The subjective visual analysis shows that the image dehazed with the image dehazing network we proposed is more similar to the real no-haze image in terms of detail, color, contrast and so on.
format Article
id doaj-art-cdf442d2f8be410c9d895370abe0979b
institution OA Journals
issn 1000-2758
2609-7125
language zho
publishDate 2025-02-01
publisher EDP Sciences
record_format Article
series Xibei Gongye Daxue Xuebao
spelling doaj-art-cdf442d2f8be410c9d895370abe0979b2025-08-20T01:53:06ZzhoEDP SciencesXibei Gongye Daxue Xuebao1000-27582609-71252025-02-0143110911810.1051/jnwpu/20254310109jnwpu2025431p109Image dehazing based on double branch convolution and detail enhancementZHAI Fengwen0ZHU Yutong1JIN Jing2School of Electronic and Information Engineering, Lanzhou Jiaotong UniversitySchool of Electronic and Information Engineering, Lanzhou Jiaotong UniversitySchool of Electronic and Information Engineering, Lanzhou Jiaotong UniversityBecause of detail loss, color distortion and contrast reduction in the image dehazing process in a haze condition, we proposed the image dehazing network based on double branch convolution and detail enhancement, which consists of image dehazing module and detail enhancement module. First, in the image dehazing module, we designed a double branch convolutional block based on depth-separable convolution and differential convolution and then combined it with the U-Net network, effectively reducing the detail loss in the image dehazing process. In the image dehazing model, we introduced the attention module composed of channel attention mechanism and pixel attention mechanism, which improves its feature extraction ability, suppresses the features that are not related to the current task and further reduces the color distortion and contrast in the image dehazing process. Then, we input the image dehazed with the image dehazing module into the detail enhancement module to further recover image details, so that the image is more similar to that in its real domain. The combination of the image dehazing module with the detail enhancement module improves the generalization ability of the image dehazing network and makes it more adaptable to the haze dataset. We carried out experiments with the public datasets ITS and Haze4K and the public real dataset IHAZE. The quantitative objective analysis and comparison show that the peak signal-to-noise ratio and the structural similarity index reach 39.69 dB and 0.994 respectively, indicating that there is a certain improvement compared with the optimal algorithm in the comparison network model. The subjective visual analysis shows that the image dehazed with the image dehazing network we proposed is more similar to the real no-haze image in terms of detail, color, contrast and so on.https://www.jnwpu.org/articles/jnwpu/full_html/2025/01/jnwpu2025431p109/jnwpu2025431p109.htmldifference convolutiondepth-separable convolutionimage dehazingattention mechanism
spellingShingle ZHAI Fengwen
ZHU Yutong
JIN Jing
Image dehazing based on double branch convolution and detail enhancement
Xibei Gongye Daxue Xuebao
difference convolution
depth-separable convolution
image dehazing
attention mechanism
title Image dehazing based on double branch convolution and detail enhancement
title_full Image dehazing based on double branch convolution and detail enhancement
title_fullStr Image dehazing based on double branch convolution and detail enhancement
title_full_unstemmed Image dehazing based on double branch convolution and detail enhancement
title_short Image dehazing based on double branch convolution and detail enhancement
title_sort image dehazing based on double branch convolution and detail enhancement
topic difference convolution
depth-separable convolution
image dehazing
attention mechanism
url https://www.jnwpu.org/articles/jnwpu/full_html/2025/01/jnwpu2025431p109/jnwpu2025431p109.html
work_keys_str_mv AT zhaifengwen imagedehazingbasedondoublebranchconvolutionanddetailenhancement
AT zhuyutong imagedehazingbasedondoublebranchconvolutionanddetailenhancement
AT jinjing imagedehazingbasedondoublebranchconvolutionanddetailenhancement