AUIE–GAN: Adaptive Underwater Image Enhancement Based on Generative Adversarial Networks
Underwater optical imaging devices are often affected by the complex underwater environment and the characteristics of the water column, which leads to serious degradation and distortion of the images they capture. Deep learning-based underwater image enhancement (UIE) methods reduce the reliance on...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/11/7/1476 |
| _version_ | 1797588718476853248 |
|---|---|
| author | Fengxu Guan Siqi Lu Haitao Lai Xue Du |
| author_facet | Fengxu Guan Siqi Lu Haitao Lai Xue Du |
| author_sort | Fengxu Guan |
| collection | DOAJ |
| description | Underwater optical imaging devices are often affected by the complex underwater environment and the characteristics of the water column, which leads to serious degradation and distortion of the images they capture. Deep learning-based underwater image enhancement (UIE) methods reduce the reliance on physical parameters in traditional methods and have powerful fitting capabilities, becoming a new baseline method for UIE tasks. However, the results of these methods often suffer from color distortion and lack of realism because they tend to have poor generalization and self-adaptation capabilities. Generating adversarial networks (GANs) provides a better fit and shows powerful capabilities on UIE tasks. Therefore, we designed a new network structure for the UIE task based on GANs. In this work, we changed the learning of the self-attention mechanism by introducing a trainable weight to balance the effect of the mechanism, improving the self-adaptive capability of the model. In addition, we designed a feature extractor based on residuals with multi-level residuals for better feature recovery. To further improve the performance of the generator, we proposed a dual path discriminator and a loss function with multiple weighted fusions to help model fitting in the frequency domain, improving image quality. We evaluated our method on the UIE task using challenging real underwater image datasets and a synthetic image dataset and compared it to state-of-the-art models. The method ensures increased enhancement quality, and the enhancement effect of the model for different styles of images is also relatively stable. |
| first_indexed | 2024-03-11T00:56:00Z |
| format | Article |
| id | doaj.art-b077fcfa31b04540962c623d78e3f322 |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-11T00:56:00Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-b077fcfa31b04540962c623d78e3f3222023-11-18T20:00:56ZengMDPI AGJournal of Marine Science and Engineering2077-13122023-07-01117147610.3390/jmse11071476AUIE–GAN: Adaptive Underwater Image Enhancement Based on Generative Adversarial NetworksFengxu Guan0Siqi Lu1Haitao Lai2Xue Du3College 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, ChinaUnderwater optical imaging devices are often affected by the complex underwater environment and the characteristics of the water column, which leads to serious degradation and distortion of the images they capture. Deep learning-based underwater image enhancement (UIE) methods reduce the reliance on physical parameters in traditional methods and have powerful fitting capabilities, becoming a new baseline method for UIE tasks. However, the results of these methods often suffer from color distortion and lack of realism because they tend to have poor generalization and self-adaptation capabilities. Generating adversarial networks (GANs) provides a better fit and shows powerful capabilities on UIE tasks. Therefore, we designed a new network structure for the UIE task based on GANs. In this work, we changed the learning of the self-attention mechanism by introducing a trainable weight to balance the effect of the mechanism, improving the self-adaptive capability of the model. In addition, we designed a feature extractor based on residuals with multi-level residuals for better feature recovery. To further improve the performance of the generator, we proposed a dual path discriminator and a loss function with multiple weighted fusions to help model fitting in the frequency domain, improving image quality. We evaluated our method on the UIE task using challenging real underwater image datasets and a synthetic image dataset and compared it to state-of-the-art models. The method ensures increased enhancement quality, and the enhancement effect of the model for different styles of images is also relatively stable.https://www.mdpi.com/2077-1312/11/7/1476underwater image enhancement (UIE)underwater image recovery (UIR)generative adversarial networks (GANs)deep learningadaptive enhancement |
| spellingShingle | Fengxu Guan Siqi Lu Haitao Lai Xue Du AUIE–GAN: Adaptive Underwater Image Enhancement Based on Generative Adversarial Networks Journal of Marine Science and Engineering underwater image enhancement (UIE) underwater image recovery (UIR) generative adversarial networks (GANs) deep learning adaptive enhancement |
| title | AUIE–GAN: Adaptive Underwater Image Enhancement Based on Generative Adversarial Networks |
| title_full | AUIE–GAN: Adaptive Underwater Image Enhancement Based on Generative Adversarial Networks |
| title_fullStr | AUIE–GAN: Adaptive Underwater Image Enhancement Based on Generative Adversarial Networks |
| title_full_unstemmed | AUIE–GAN: Adaptive Underwater Image Enhancement Based on Generative Adversarial Networks |
| title_short | AUIE–GAN: Adaptive Underwater Image Enhancement Based on Generative Adversarial Networks |
| title_sort | auie gan adaptive underwater image enhancement based on generative adversarial networks |
| topic | underwater image enhancement (UIE) underwater image recovery (UIR) generative adversarial networks (GANs) deep learning adaptive enhancement |
| url | https://www.mdpi.com/2077-1312/11/7/1476 |
| work_keys_str_mv | AT fengxuguan auieganadaptiveunderwaterimageenhancementbasedongenerativeadversarialnetworks AT siqilu auieganadaptiveunderwaterimageenhancementbasedongenerativeadversarialnetworks AT haitaolai auieganadaptiveunderwaterimageenhancementbasedongenerativeadversarialnetworks AT xuedu auieganadaptiveunderwaterimageenhancementbasedongenerativeadversarialnetworks |