RGB-Net: transformer-based lightweight low-light image enhancement network via RGB channel separation: RGB-Net: transformer-based lightweight low-light image...: J. Zhang et al.
Saved in:
| Title: | RGB-Net: transformer-based lightweight low-light image enhancement network via RGB channel separation: RGB-Net: transformer-based lightweight low-light image...: J. Zhang et al. |
|---|---|
| Authors: | Zhang, Jianming1,2 (AUTHOR) jmzhang@csust.edu.cn, Feng, Zhijian1,2 (AUTHOR) fzj@stu.csust.edu.cn, Jiang, Jia1,2 (AUTHOR) jiangjia@stu.csust.edu.cn, Shi, Xiangnan1,2 (AUTHOR) 23108011675@stu.csust.edu.cn, Zhang, Jin2 (AUTHOR) jzhang@csust.edu.cn |
| Source: | Multimedia Systems. Jun2025, Vol. 31 Issue 3, p1-14. 14p. |
| Subjects: | Image intensifiers, Artificial intelligence, Image reconstruction, Feature extraction, Transformer models, Image enhancement (Imaging systems) |
| Abstract: | In real-life scenarios, captured images often suffer from insufficient brightness, significant noise, and color distortion due to varying lighting conditions. Therefore, we propose a novel lightweight network for low-light image enhancement named RGB-Net. Firstly, unlike traditional Retinex-based models, our approach leverages the separation of RGB color channels to enhance the input image. Each RGB channel is independently enhanced for brightness and color information by a U-shaped channel optimization module (UCOM). Additionally, we utilize the transformer to capture long-range dependencies by incorporating a multi-head self-attention module within the UCOM, thereby improving feature extraction capabilities. Secondly, we design a multi-channel fusion module (MCFM) that integrates a mixed dense convolution and fully connected layers, employing a residual network to fuse the enhancement results from different color channels for improve image reconstruction. Thirdly, we construct a new hybrid loss function by exploring various loss terms, which significantly improves the representational ability of our network. Extensive experiments on five publicly used real-world datasets have shown that our method can significantly enhance image details with only 0.71M parameters and 5.81G floating-point operations, outperforming existing low-light image enhancement algorithms in both quantitative and qualitative evaluations. [ABSTRACT FROM AUTHOR] |
| Copyright of Multimedia Systems is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | In real-life scenarios, captured images often suffer from insufficient brightness, significant noise, and color distortion due to varying lighting conditions. Therefore, we propose a novel lightweight network for low-light image enhancement named RGB-Net. Firstly, unlike traditional Retinex-based models, our approach leverages the separation of RGB color channels to enhance the input image. Each RGB channel is independently enhanced for brightness and color information by a U-shaped channel optimization module (UCOM). Additionally, we utilize the transformer to capture long-range dependencies by incorporating a multi-head self-attention module within the UCOM, thereby improving feature extraction capabilities. Secondly, we design a multi-channel fusion module (MCFM) that integrates a mixed dense convolution and fully connected layers, employing a residual network to fuse the enhancement results from different color channels for improve image reconstruction. Thirdly, we construct a new hybrid loss function by exploring various loss terms, which significantly improves the representational ability of our network. Extensive experiments on five publicly used real-world datasets have shown that our method can significantly enhance image details with only 0.71M parameters and 5.81G floating-point operations, outperforming existing low-light image enhancement algorithms in both quantitative and qualitative evaluations. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 09424962 |
| DOI: | 10.1007/s00530-025-01750-4 |
