Area Contrast Distribution Loss for Underwater Image Enhancement
In this paper, we aim to design a lightweight underwater image enhancement algorithm that can effectively solve the problem of color distortion and low contrast in underwater images. Recently, enhancement methods typically optimize a perceptual loss function, using high-level features extracted from...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/11/5/909 |
| _version_ | 1797599630921302016 |
|---|---|
| author | Jiajia Zhou Junbin Zhuang Yan Zheng Juan Li |
| author_facet | Jiajia Zhou Junbin Zhuang Yan Zheng Juan Li |
| author_sort | Jiajia Zhou |
| collection | DOAJ |
| description | In this paper, we aim to design a lightweight underwater image enhancement algorithm that can effectively solve the problem of color distortion and low contrast in underwater images. Recently, enhancement methods typically optimize a perceptual loss function, using high-level features extracted from pre-trained networks to train a feed-forward network for image enhancement tasks. This loss function measures the perceptual and semantic differences between images, but it is applied globally across the entire image and does not consider semantic information within the image, which limits the effectiveness of the perceptual loss. Therefore, we propose an area contrast distribution loss (ACDL), which trains a flow model to achieve real-time optimization of the difference between output and reference in training. Additionally, we propose a novel lightweight neural network. Because underwater image acquisition is difficult, our experiments have shown that our model training can use only half the amount of data and half the image size compared to Shallow-UWnet. The RepNet network reduces the parameter size by at least 48% compared to previous algorithms, and the inference time is 5 times faster than before. After incorporating ACDL, SSIM increased by 2.70% and PSNR increased by 9.72%. |
| first_indexed | 2024-03-11T03:36:59Z |
| format | Article |
| id | doaj.art-ee1dd6b883c14eafa2ec9994ea3fbdf1 |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-11T03:36:59Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-ee1dd6b883c14eafa2ec9994ea3fbdf12023-11-18T01:58:18ZengMDPI AGJournal of Marine Science and Engineering2077-13122023-04-0111590910.3390/jmse11050909Area Contrast Distribution Loss for Underwater Image EnhancementJiajia Zhou0Junbin Zhuang1Yan Zheng2Juan Li3College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150001, ChinaCollege of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150001, ChinaCollege of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150001, ChinaCollege of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150001, ChinaIn this paper, we aim to design a lightweight underwater image enhancement algorithm that can effectively solve the problem of color distortion and low contrast in underwater images. Recently, enhancement methods typically optimize a perceptual loss function, using high-level features extracted from pre-trained networks to train a feed-forward network for image enhancement tasks. This loss function measures the perceptual and semantic differences between images, but it is applied globally across the entire image and does not consider semantic information within the image, which limits the effectiveness of the perceptual loss. Therefore, we propose an area contrast distribution loss (ACDL), which trains a flow model to achieve real-time optimization of the difference between output and reference in training. Additionally, we propose a novel lightweight neural network. Because underwater image acquisition is difficult, our experiments have shown that our model training can use only half the amount of data and half the image size compared to Shallow-UWnet. The RepNet network reduces the parameter size by at least 48% compared to previous algorithms, and the inference time is 5 times faster than before. After incorporating ACDL, SSIM increased by 2.70% and PSNR increased by 9.72%.https://www.mdpi.com/2077-1312/11/5/909underwater image enhancementlightweight neural networkperceptual loss functionreal time |
| spellingShingle | Jiajia Zhou Junbin Zhuang Yan Zheng Juan Li Area Contrast Distribution Loss for Underwater Image Enhancement Journal of Marine Science and Engineering underwater image enhancement lightweight neural network perceptual loss function real time |
| title | Area Contrast Distribution Loss for Underwater Image Enhancement |
| title_full | Area Contrast Distribution Loss for Underwater Image Enhancement |
| title_fullStr | Area Contrast Distribution Loss for Underwater Image Enhancement |
| title_full_unstemmed | Area Contrast Distribution Loss for Underwater Image Enhancement |
| title_short | Area Contrast Distribution Loss for Underwater Image Enhancement |
| title_sort | area contrast distribution loss for underwater image enhancement |
| topic | underwater image enhancement lightweight neural network perceptual loss function real time |
| url | https://www.mdpi.com/2077-1312/11/5/909 |
| work_keys_str_mv | AT jiajiazhou areacontrastdistributionlossforunderwaterimageenhancement AT junbinzhuang areacontrastdistributionlossforunderwaterimageenhancement AT yanzheng areacontrastdistributionlossforunderwaterimageenhancement AT juanli areacontrastdistributionlossforunderwaterimageenhancement |