A novel edge-feature attention fusion framework for underwater image enhancement
Underwater images captured by Remotely Operated Vehicles are critical for marine research, ocean engineering, and national defense, but challenges such as blurriness and color distortion necessitate advanced enhancement techniques. To address these issues, this paper presents the CUG-UIEF algorithm,...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-04-01
|
| Series: | Frontiers in Marine Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmars.2025.1555286/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849736947887505408 |
|---|---|
| author | Shuai Shen Haoyi Wang Weitao Chen Pingkang Wang Qianyong Liang Xuwen Qin Xuwen Qin |
| author_facet | Shuai Shen Haoyi Wang Weitao Chen Pingkang Wang Qianyong Liang Xuwen Qin Xuwen Qin |
| author_sort | Shuai Shen |
| collection | DOAJ |
| description | Underwater images captured by Remotely Operated Vehicles are critical for marine research, ocean engineering, and national defense, but challenges such as blurriness and color distortion necessitate advanced enhancement techniques. To address these issues, this paper presents the CUG-UIEF algorithm, an underwater image enhancement framework leveraging edge feature attention fusion. The method comprises three modules: 1) an Attention-Guided Edge Feature Fusion Module that extracts edge information via edge operators and enhances object detail through multi-scale feature integration with channel-cross attention to resolve edge blurring; 2) a Spatial Information Enhancement Module that employs spatial-cross attention to capture spatial interrelationships and improve semantic representation, mitigating low signal-to-noise ratio; and 3) Multi-Dimensional Perception Optimization integrating perceptual, structural, and anomaly optimizations to address detail blurring and low contrast. Experimental results demonstrate that CUG-UIEF achieves an average peak signal-to-noise ratio of 24.49 dB, an 8.41% improvement over six mainstream algorithms, and a structural similarity index of 0.92, a 1.09% increase. These findings highlight the model’s effectiveness in balancing edge preservation, spatial semantics, and perceptual quality, offering promising applications in marine science and related fields. |
| format | Article |
| id | doaj-art-3c0252ecfed24fbe993322cef99b66e0 |
| institution | DOAJ |
| issn | 2296-7745 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Marine Science |
| spelling | doaj-art-3c0252ecfed24fbe993322cef99b66e02025-08-20T03:07:06ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452025-04-011210.3389/fmars.2025.15552861555286A novel edge-feature attention fusion framework for underwater image enhancementShuai Shen0Haoyi Wang1Weitao Chen2Pingkang Wang3Qianyong Liang4Xuwen Qin5Xuwen Qin6Faculty of Computer-Science, China University of Geosciences, Wuhan, Hubei, ChinaFaculty of Computer-Science, China University of Geosciences, Wuhan, Hubei, ChinaFaculty of Computer-Science, China University of Geosciences, Wuhan, Hubei, ChinaDepartment of Fundamental Investigations, China Geological Survey, Beijing, ChinaGuangzhou Marine Geological Survey, China Geological Survey, Guangzhou, Guangdong, ChinaKey Laboratory of Geological Survey and Evaluation of Ministry of Education, China University of Geosciences, Wuhan, Hubei, ChinaChina Aero Geophysical Survey and Remote Sensing Centre for Natural Resources, China Geological Survey, Beijing, ChinaUnderwater images captured by Remotely Operated Vehicles are critical for marine research, ocean engineering, and national defense, but challenges such as blurriness and color distortion necessitate advanced enhancement techniques. To address these issues, this paper presents the CUG-UIEF algorithm, an underwater image enhancement framework leveraging edge feature attention fusion. The method comprises three modules: 1) an Attention-Guided Edge Feature Fusion Module that extracts edge information via edge operators and enhances object detail through multi-scale feature integration with channel-cross attention to resolve edge blurring; 2) a Spatial Information Enhancement Module that employs spatial-cross attention to capture spatial interrelationships and improve semantic representation, mitigating low signal-to-noise ratio; and 3) Multi-Dimensional Perception Optimization integrating perceptual, structural, and anomaly optimizations to address detail blurring and low contrast. Experimental results demonstrate that CUG-UIEF achieves an average peak signal-to-noise ratio of 24.49 dB, an 8.41% improvement over six mainstream algorithms, and a structural similarity index of 0.92, a 1.09% increase. These findings highlight the model’s effectiveness in balancing edge preservation, spatial semantics, and perceptual quality, offering promising applications in marine science and related fields.https://www.frontiersin.org/articles/10.3389/fmars.2025.1555286/fullunderwater image enhancementedge feature attention fusionspatial crossattentionmultidimensional perception optimizationattention-guided edge feature fusion |
| spellingShingle | Shuai Shen Haoyi Wang Weitao Chen Pingkang Wang Qianyong Liang Xuwen Qin Xuwen Qin A novel edge-feature attention fusion framework for underwater image enhancement Frontiers in Marine Science underwater image enhancement edge feature attention fusion spatial crossattention multidimensional perception optimization attention-guided edge feature fusion |
| title | A novel edge-feature attention fusion framework for underwater image enhancement |
| title_full | A novel edge-feature attention fusion framework for underwater image enhancement |
| title_fullStr | A novel edge-feature attention fusion framework for underwater image enhancement |
| title_full_unstemmed | A novel edge-feature attention fusion framework for underwater image enhancement |
| title_short | A novel edge-feature attention fusion framework for underwater image enhancement |
| title_sort | novel edge feature attention fusion framework for underwater image enhancement |
| topic | underwater image enhancement edge feature attention fusion spatial crossattention multidimensional perception optimization attention-guided edge feature fusion |
| url | https://www.frontiersin.org/articles/10.3389/fmars.2025.1555286/full |
| work_keys_str_mv | AT shuaishen anoveledgefeatureattentionfusionframeworkforunderwaterimageenhancement AT haoyiwang anoveledgefeatureattentionfusionframeworkforunderwaterimageenhancement AT weitaochen anoveledgefeatureattentionfusionframeworkforunderwaterimageenhancement AT pingkangwang anoveledgefeatureattentionfusionframeworkforunderwaterimageenhancement AT qianyongliang anoveledgefeatureattentionfusionframeworkforunderwaterimageenhancement AT xuwenqin anoveledgefeatureattentionfusionframeworkforunderwaterimageenhancement AT xuwenqin anoveledgefeatureattentionfusionframeworkforunderwaterimageenhancement AT shuaishen noveledgefeatureattentionfusionframeworkforunderwaterimageenhancement AT haoyiwang noveledgefeatureattentionfusionframeworkforunderwaterimageenhancement AT weitaochen noveledgefeatureattentionfusionframeworkforunderwaterimageenhancement AT pingkangwang noveledgefeatureattentionfusionframeworkforunderwaterimageenhancement AT qianyongliang noveledgefeatureattentionfusionframeworkforunderwaterimageenhancement AT xuwenqin noveledgefeatureattentionfusionframeworkforunderwaterimageenhancement AT xuwenqin noveledgefeatureattentionfusionframeworkforunderwaterimageenhancement |