sRrsR-Net: A New Low-Light Image Enhancement Network via Raw Image Reconstruction
Most existing low-light image enhancement (LIE) methods are primarily designed for human-vision-friendly image formats, such as sRGB, due to their convenient storage and smaller file sizes. In addition, raw images provide greater detail and a wider dynamic range, which makes them more suitable for L...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/1/361 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549345034338304 |
|---|---|
| author | Zhiyong Hong Dexin Zhen Liping Xiong Xuechen Li Yuhan Lin |
| author_facet | Zhiyong Hong Dexin Zhen Liping Xiong Xuechen Li Yuhan Lin |
| author_sort | Zhiyong Hong |
| collection | DOAJ |
| description | Most existing low-light image enhancement (LIE) methods are primarily designed for human-vision-friendly image formats, such as sRGB, due to their convenient storage and smaller file sizes. In addition, raw images provide greater detail and a wider dynamic range, which makes them more suitable for LIE tasks. Despite these advantages, raw images, the original format captured by cameras, are larger and less accessible and are hard to use in methods of LIE with mobile devices. In order to leverage both the advantages of sRGB and raw domains while avoiding the direct use of raw images as training data, this paper introduces sRrsR-Net, a novel framework with the image translation process of sRGB–raw–sRGB for LIE task. In our approach, firstly, the RGB-to-iRGB module is designed to convert sRGB images into intermediate RGB feature maps. Then, with these intermediate feature maps, to bridge the domain gap between sRGB and raw pixels, the RAWFormer module is proposed to employ global attention to effectively align features between the two domains to generate reconstructed raw images. For enhancing the raw images and restoring them back to normal-light sRGB, unlike traditional Image Signal Processing (ISP) pipelines, which are often bulky and integrate numerous processing steps, we propose the RRAW-to-sRGB module. This module simplifies the process by focusing only on color correction and white balance, while still delivering competitive results. Extensive experiments on four benchmark datasets referring to both domains demonstrate the effectiveness of our approach. |
| format | Article |
| id | doaj-art-50d0f8f940a04846b9703a065d86152f |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-50d0f8f940a04846b9703a065d86152f2025-01-10T13:15:17ZengMDPI AGApplied Sciences2076-34172025-01-0115136110.3390/app15010361sRrsR-Net: A New Low-Light Image Enhancement Network via Raw Image ReconstructionZhiyong Hong0Dexin Zhen1Liping Xiong2Xuechen Li3Yuhan Lin4College of Electronic and Information Engineering, Wuyi University, Jiangmen 529000, ChinaCollege of Electronic and Information Engineering, Wuyi University, Jiangmen 529000, ChinaCollege of Electronic and Information Engineering, Wuyi University, Jiangmen 529000, ChinaCollege of Electronic and Information Engineering, Wuyi University, Jiangmen 529000, ChinaCollege of Electronic and Information Engineering, Wuyi University, Jiangmen 529000, ChinaMost existing low-light image enhancement (LIE) methods are primarily designed for human-vision-friendly image formats, such as sRGB, due to their convenient storage and smaller file sizes. In addition, raw images provide greater detail and a wider dynamic range, which makes them more suitable for LIE tasks. Despite these advantages, raw images, the original format captured by cameras, are larger and less accessible and are hard to use in methods of LIE with mobile devices. In order to leverage both the advantages of sRGB and raw domains while avoiding the direct use of raw images as training data, this paper introduces sRrsR-Net, a novel framework with the image translation process of sRGB–raw–sRGB for LIE task. In our approach, firstly, the RGB-to-iRGB module is designed to convert sRGB images into intermediate RGB feature maps. Then, with these intermediate feature maps, to bridge the domain gap between sRGB and raw pixels, the RAWFormer module is proposed to employ global attention to effectively align features between the two domains to generate reconstructed raw images. For enhancing the raw images and restoring them back to normal-light sRGB, unlike traditional Image Signal Processing (ISP) pipelines, which are often bulky and integrate numerous processing steps, we propose the RRAW-to-sRGB module. This module simplifies the process by focusing only on color correction and white balance, while still delivering competitive results. Extensive experiments on four benchmark datasets referring to both domains demonstrate the effectiveness of our approach.https://www.mdpi.com/2076-3417/15/1/361low-light image enhancementimage signal processingglobal attentionraw image |
| spellingShingle | Zhiyong Hong Dexin Zhen Liping Xiong Xuechen Li Yuhan Lin sRrsR-Net: A New Low-Light Image Enhancement Network via Raw Image Reconstruction Applied Sciences low-light image enhancement image signal processing global attention raw image |
| title | sRrsR-Net: A New Low-Light Image Enhancement Network via Raw Image Reconstruction |
| title_full | sRrsR-Net: A New Low-Light Image Enhancement Network via Raw Image Reconstruction |
| title_fullStr | sRrsR-Net: A New Low-Light Image Enhancement Network via Raw Image Reconstruction |
| title_full_unstemmed | sRrsR-Net: A New Low-Light Image Enhancement Network via Raw Image Reconstruction |
| title_short | sRrsR-Net: A New Low-Light Image Enhancement Network via Raw Image Reconstruction |
| title_sort | srrsr net a new low light image enhancement network via raw image reconstruction |
| topic | low-light image enhancement image signal processing global attention raw image |
| url | https://www.mdpi.com/2076-3417/15/1/361 |
| work_keys_str_mv | AT zhiyonghong srrsrnetanewlowlightimageenhancementnetworkviarawimagereconstruction AT dexinzhen srrsrnetanewlowlightimageenhancementnetworkviarawimagereconstruction AT lipingxiong srrsrnetanewlowlightimageenhancementnetworkviarawimagereconstruction AT xuechenli srrsrnetanewlowlightimageenhancementnetworkviarawimagereconstruction AT yuhanlin srrsrnetanewlowlightimageenhancementnetworkviarawimagereconstruction |