DEGAN: Decompose-Enhance-GAN Network for Simultaneous Low-Light Image Lightening and Denoising
Images taken in low-light situations frequently have a significant quality reduction. Taking care of these degradation problems in low-light images is essential for raising their visual quality and enhancing high-level visual task performance. However, because of the inherent information loss in dar...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/14/3038 |
| _version_ | 1797589522437898240 |
|---|---|
| author | Jialiang Zhang Ruiwen Ji Jingwen Wang Hongcheng Sun Mingye Ju |
| author_facet | Jialiang Zhang Ruiwen Ji Jingwen Wang Hongcheng Sun Mingye Ju |
| author_sort | Jialiang Zhang |
| collection | DOAJ |
| description | Images taken in low-light situations frequently have a significant quality reduction. Taking care of these degradation problems in low-light images is essential for raising their visual quality and enhancing high-level visual task performance. However, because of the inherent information loss in dark images, conventional Retinex-based approaches for low-light image enhancement frequently fail to accomplish real denoising. This research introduces DEGANet, a revolutionary deep-learning framework created particularly for improving and denoising low-light images. To overcome these restrictions, DEGANet makes use of the strength of a Generative Adversarial Network (GAN). The Decom-Net, Enhance-Net, and an Adversarial Generative Network (GAN) are three linked subnets that make up our novel Retinex-based DEGANet architecture. The Decom-Net is in charge of separating the reflectance and illumination components from the input low-light image. This decomposition enables Enhance-Net to effectively enhance the illumination component, thereby improving the overall image quality. Due to the complicated noise patterns, fluctuating intensities, and intrinsic information loss in low-light images, denoising them presents a significant challenge. By incorporating a GAN into our architecture, DEGANet is able to effectively denoise and smooth the enhanced image as well as retrieve the original data and fill in the gaps, producing an output that is aesthetically beautiful while maintaining key features. Through a comprehensive set of studies, we demonstrate that DEGANet exceeds current state-of-the-art methods in both terms of image enhancement and denoising quality. |
| first_indexed | 2024-03-11T01:07:40Z |
| format | Article |
| id | doaj.art-59836e8864dc43baa26d0d1b4cd38f11 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T01:07:40Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-59836e8864dc43baa26d0d1b4cd38f112023-11-18T19:04:55ZengMDPI AGElectronics2079-92922023-07-011214303810.3390/electronics12143038DEGAN: Decompose-Enhance-GAN Network for Simultaneous Low-Light Image Lightening and DenoisingJialiang Zhang0Ruiwen Ji1Jingwen Wang2Hongcheng Sun3Mingye Ju4School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210046, ChinaSchool of Mathematics and Science, Shanghai Normal University, Shanghai 200234, ChinaSchool of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210046, ChinaSchool of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210046, ChinaSchool of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210046, ChinaImages taken in low-light situations frequently have a significant quality reduction. Taking care of these degradation problems in low-light images is essential for raising their visual quality and enhancing high-level visual task performance. However, because of the inherent information loss in dark images, conventional Retinex-based approaches for low-light image enhancement frequently fail to accomplish real denoising. This research introduces DEGANet, a revolutionary deep-learning framework created particularly for improving and denoising low-light images. To overcome these restrictions, DEGANet makes use of the strength of a Generative Adversarial Network (GAN). The Decom-Net, Enhance-Net, and an Adversarial Generative Network (GAN) are three linked subnets that make up our novel Retinex-based DEGANet architecture. The Decom-Net is in charge of separating the reflectance and illumination components from the input low-light image. This decomposition enables Enhance-Net to effectively enhance the illumination component, thereby improving the overall image quality. Due to the complicated noise patterns, fluctuating intensities, and intrinsic information loss in low-light images, denoising them presents a significant challenge. By incorporating a GAN into our architecture, DEGANet is able to effectively denoise and smooth the enhanced image as well as retrieve the original data and fill in the gaps, producing an output that is aesthetically beautiful while maintaining key features. Through a comprehensive set of studies, we demonstrate that DEGANet exceeds current state-of-the-art methods in both terms of image enhancement and denoising quality.https://www.mdpi.com/2079-9292/12/14/3038retinex theoryadversarial generative network (GAN)low-light image enhancementimage processing |
| spellingShingle | Jialiang Zhang Ruiwen Ji Jingwen Wang Hongcheng Sun Mingye Ju DEGAN: Decompose-Enhance-GAN Network for Simultaneous Low-Light Image Lightening and Denoising Electronics retinex theory adversarial generative network (GAN) low-light image enhancement image processing |
| title | DEGAN: Decompose-Enhance-GAN Network for Simultaneous Low-Light Image Lightening and Denoising |
| title_full | DEGAN: Decompose-Enhance-GAN Network for Simultaneous Low-Light Image Lightening and Denoising |
| title_fullStr | DEGAN: Decompose-Enhance-GAN Network for Simultaneous Low-Light Image Lightening and Denoising |
| title_full_unstemmed | DEGAN: Decompose-Enhance-GAN Network for Simultaneous Low-Light Image Lightening and Denoising |
| title_short | DEGAN: Decompose-Enhance-GAN Network for Simultaneous Low-Light Image Lightening and Denoising |
| title_sort | degan decompose enhance gan network for simultaneous low light image lightening and denoising |
| topic | retinex theory adversarial generative network (GAN) low-light image enhancement image processing |
| url | https://www.mdpi.com/2079-9292/12/14/3038 |
| work_keys_str_mv | AT jialiangzhang degandecomposeenhancegannetworkforsimultaneouslowlightimagelighteninganddenoising AT ruiwenji degandecomposeenhancegannetworkforsimultaneouslowlightimagelighteninganddenoising AT jingwenwang degandecomposeenhancegannetworkforsimultaneouslowlightimagelighteninganddenoising AT hongchengsun degandecomposeenhancegannetworkforsimultaneouslowlightimagelighteninganddenoising AT mingyeju degandecomposeenhancegannetworkforsimultaneouslowlightimagelighteninganddenoising |