Multi-Scale Attention Feature Enhancement Network for Single Image Dehazing
Aiming to solve the problem of color distortion and loss of detail information in most dehazing algorithms, an end-to-end image dehazing network based on multi-scale feature enhancement is proposed. Firstly, the feature extraction enhancement module is used to capture the detailed information of haz...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/19/8102 |
| _version_ | 1797575127030824960 |
|---|---|
| author | Weida Dong Chunyan Wang Hao Sun Yunjie Teng Xiping Xu |
| author_facet | Weida Dong Chunyan Wang Hao Sun Yunjie Teng Xiping Xu |
| author_sort | Weida Dong |
| collection | DOAJ |
| description | Aiming to solve the problem of color distortion and loss of detail information in most dehazing algorithms, an end-to-end image dehazing network based on multi-scale feature enhancement is proposed. Firstly, the feature extraction enhancement module is used to capture the detailed information of hazy images and expand the receptive field. Secondly, the channel attention mechanism and pixel attention mechanism of the feature fusion enhancement module are used to dynamically adjust the weights of different channels and pixels. Thirdly, the context enhancement module is used to enhance the context semantic information, suppress redundant information, and obtain the haze density image with higher detail. Finally, our method removes haze, preserves image color, and ensures image details. The proposed method achieved a PSNR score of 33.74, SSIM scores of 0.9843 and LPIPS distance of 0.0040 on the SOTS-outdoor dataset. Compared with representative dehazing methods, it demonstrates better dehazing performance and proves the advantages of the proposed method on synthetic hazy images. Combined with dehazing experiments on real hazy images, the results show that our method can effectively improve dehazing performance while preserving more image details and achieving color fidelity. |
| first_indexed | 2024-03-10T21:35:14Z |
| format | Article |
| id | doaj.art-04c9c12ba6ec4009a4897078e5139b32 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T21:35:14Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-04c9c12ba6ec4009a4897078e5139b322023-11-19T15:02:45ZengMDPI AGSensors1424-82202023-09-012319810210.3390/s23198102Multi-Scale Attention Feature Enhancement Network for Single Image DehazingWeida Dong0Chunyan Wang1Hao Sun2Yunjie Teng3Xiping Xu4School of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun 130022, ChinaSchool of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun 130022, ChinaSchool of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun 130022, ChinaSchool of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun 130022, ChinaSchool of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun 130022, ChinaAiming to solve the problem of color distortion and loss of detail information in most dehazing algorithms, an end-to-end image dehazing network based on multi-scale feature enhancement is proposed. Firstly, the feature extraction enhancement module is used to capture the detailed information of hazy images and expand the receptive field. Secondly, the channel attention mechanism and pixel attention mechanism of the feature fusion enhancement module are used to dynamically adjust the weights of different channels and pixels. Thirdly, the context enhancement module is used to enhance the context semantic information, suppress redundant information, and obtain the haze density image with higher detail. Finally, our method removes haze, preserves image color, and ensures image details. The proposed method achieved a PSNR score of 33.74, SSIM scores of 0.9843 and LPIPS distance of 0.0040 on the SOTS-outdoor dataset. Compared with representative dehazing methods, it demonstrates better dehazing performance and proves the advantages of the proposed method on synthetic hazy images. Combined with dehazing experiments on real hazy images, the results show that our method can effectively improve dehazing performance while preserving more image details and achieving color fidelity.https://www.mdpi.com/1424-8220/23/19/8102image dehazingimage restorationfeature enhancementcolor fidelity |
| spellingShingle | Weida Dong Chunyan Wang Hao Sun Yunjie Teng Xiping Xu Multi-Scale Attention Feature Enhancement Network for Single Image Dehazing Sensors image dehazing image restoration feature enhancement color fidelity |
| title | Multi-Scale Attention Feature Enhancement Network for Single Image Dehazing |
| title_full | Multi-Scale Attention Feature Enhancement Network for Single Image Dehazing |
| title_fullStr | Multi-Scale Attention Feature Enhancement Network for Single Image Dehazing |
| title_full_unstemmed | Multi-Scale Attention Feature Enhancement Network for Single Image Dehazing |
| title_short | Multi-Scale Attention Feature Enhancement Network for Single Image Dehazing |
| title_sort | multi scale attention feature enhancement network for single image dehazing |
| topic | image dehazing image restoration feature enhancement color fidelity |
| url | https://www.mdpi.com/1424-8220/23/19/8102 |
| work_keys_str_mv | AT weidadong multiscaleattentionfeatureenhancementnetworkforsingleimagedehazing AT chunyanwang multiscaleattentionfeatureenhancementnetworkforsingleimagedehazing AT haosun multiscaleattentionfeatureenhancementnetworkforsingleimagedehazing AT yunjieteng multiscaleattentionfeatureenhancementnetworkforsingleimagedehazing AT xipingxu multiscaleattentionfeatureenhancementnetworkforsingleimagedehazing |