ICAFormer: An Image Dehazing Transformer Based on Interactive Channel Attention

Single image dehazing is a fundamental task in computer vision, aiming to recover a clear scene from a hazy input image. To address the limitations of traditional dehazing algorithms—particularly in global feature association and local detail preservation—this study proposes a novel Transformer-base...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanfei Chen, Tong Yue, Pei An, Hanyu Hong, Tao Liu, Yangkai Liu, Yihui Zhou
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/12/3750
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849433993188999168
author Yanfei Chen
Tong Yue
Pei An
Hanyu Hong
Tao Liu
Yangkai Liu
Yihui Zhou
author_facet Yanfei Chen
Tong Yue
Pei An
Hanyu Hong
Tao Liu
Yangkai Liu
Yihui Zhou
author_sort Yanfei Chen
collection DOAJ
description Single image dehazing is a fundamental task in computer vision, aiming to recover a clear scene from a hazy input image. To address the limitations of traditional dehazing algorithms—particularly in global feature association and local detail preservation—this study proposes a novel Transformer-based dehazing model enhanced by an interactive channel attention mechanism. The proposed architecture adopts a U-shaped encoder–decoder framework, incorporating key components such as a feature extraction module and a feature fusion module based on interactive attention. Specifically, the interactive channel attention mechanism facilitates cross-layer feature interaction, enabling the dynamic fusion of global contextual information and local texture details. The network architecture leverages a multi-scale feature pyramid to extract image information across different dimensions, while an improved cross-channel attention weighting mechanism enhances feature representation in regions with varying haze densities. Extensive experiments conducted on both synthetic and real-world datasets—including the RESIDE benchmark—demonstrate the superior performance of the proposed method. Quantitatively, it achieves PSNR gains of 0.53 dB for indoor scenes and 1.64 dB for outdoor scenes, alongside SSIM improvements of 1.4% and 1.7%, respectively, compared with the second-best performing method. Qualitative assessments further confirm that the proposed model excels in restoring fine structural details in dense haze regions while maintaining high color fidelity. These results validate the effectiveness of the proposed approach in enhancing both perceptual quality and quantitative accuracy in image dehazing tasks.
format Article
id doaj-art-718ff276b4f5427c8a816b43d058f46c
institution Kabale University
issn 1424-8220
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-718ff276b4f5427c8a816b43d058f46c2025-08-20T03:26:51ZengMDPI AGSensors1424-82202025-06-012512375010.3390/s25123750ICAFormer: An Image Dehazing Transformer Based on Interactive Channel AttentionYanfei Chen0Tong Yue1Pei An2Hanyu Hong3Tao Liu4Yangkai Liu5Yihui Zhou6Hubei Key Laboratory of Optical Information and Pattern Recognition, School of Electrical and Information Engineering, Wuhan Institute of Technology, Wuhan 430205, ChinaHubei Key Laboratory of Optical Information and Pattern Recognition, School of Electrical and Information Engineering, Wuhan Institute of Technology, Wuhan 430205, ChinaSchool of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430072, ChinaHubei Key Laboratory of Optical Information and Pattern Recognition, School of Electrical and Information Engineering, Wuhan Institute of Technology, Wuhan 430205, ChinaHubei Key Laboratory of Optical Information and Pattern Recognition, School of Electrical and Information Engineering, Wuhan Institute of Technology, Wuhan 430205, ChinaHubei Key Laboratory of Optical Information and Pattern Recognition, School of Electrical and Information Engineering, Wuhan Institute of Technology, Wuhan 430205, ChinaHubei Key Laboratory of Optical Information and Pattern Recognition, School of Electrical and Information Engineering, Wuhan Institute of Technology, Wuhan 430205, ChinaSingle image dehazing is a fundamental task in computer vision, aiming to recover a clear scene from a hazy input image. To address the limitations of traditional dehazing algorithms—particularly in global feature association and local detail preservation—this study proposes a novel Transformer-based dehazing model enhanced by an interactive channel attention mechanism. The proposed architecture adopts a U-shaped encoder–decoder framework, incorporating key components such as a feature extraction module and a feature fusion module based on interactive attention. Specifically, the interactive channel attention mechanism facilitates cross-layer feature interaction, enabling the dynamic fusion of global contextual information and local texture details. The network architecture leverages a multi-scale feature pyramid to extract image information across different dimensions, while an improved cross-channel attention weighting mechanism enhances feature representation in regions with varying haze densities. Extensive experiments conducted on both synthetic and real-world datasets—including the RESIDE benchmark—demonstrate the superior performance of the proposed method. Quantitatively, it achieves PSNR gains of 0.53 dB for indoor scenes and 1.64 dB for outdoor scenes, alongside SSIM improvements of 1.4% and 1.7%, respectively, compared with the second-best performing method. Qualitative assessments further confirm that the proposed model excels in restoring fine structural details in dense haze regions while maintaining high color fidelity. These results validate the effectiveness of the proposed approach in enhancing both perceptual quality and quantitative accuracy in image dehazing tasks.https://www.mdpi.com/1424-8220/25/12/3750image dehazeTransformerfeature extractionattention mechanism
spellingShingle Yanfei Chen
Tong Yue
Pei An
Hanyu Hong
Tao Liu
Yangkai Liu
Yihui Zhou
ICAFormer: An Image Dehazing Transformer Based on Interactive Channel Attention
Sensors
image dehaze
Transformer
feature extraction
attention mechanism
title ICAFormer: An Image Dehazing Transformer Based on Interactive Channel Attention
title_full ICAFormer: An Image Dehazing Transformer Based on Interactive Channel Attention
title_fullStr ICAFormer: An Image Dehazing Transformer Based on Interactive Channel Attention
title_full_unstemmed ICAFormer: An Image Dehazing Transformer Based on Interactive Channel Attention
title_short ICAFormer: An Image Dehazing Transformer Based on Interactive Channel Attention
title_sort icaformer an image dehazing transformer based on interactive channel attention
topic image dehaze
Transformer
feature extraction
attention mechanism
url https://www.mdpi.com/1424-8220/25/12/3750
work_keys_str_mv AT yanfeichen icaformeranimagedehazingtransformerbasedoninteractivechannelattention
AT tongyue icaformeranimagedehazingtransformerbasedoninteractivechannelattention
AT peian icaformeranimagedehazingtransformerbasedoninteractivechannelattention
AT hanyuhong icaformeranimagedehazingtransformerbasedoninteractivechannelattention
AT taoliu icaformeranimagedehazingtransformerbasedoninteractivechannelattention
AT yangkailiu icaformeranimagedehazingtransformerbasedoninteractivechannelattention
AT yihuizhou icaformeranimagedehazingtransformerbasedoninteractivechannelattention