CUI-Net: a correcting uneven illumination net for low-light image enhancement
Abstract Uneven lighting conditions often occur during real-life photography, such as images taken at night that may have both low-light dark areas and high-light overexposed areas. Traditional algorithms for enhancing low-light areas also increase the brightness of overexposed areas, affecting the...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-08-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-39524-5 |
| _version_ | 1797452860822126592 |
|---|---|
| author | Ke Chao Wei Song Sen Shao Dan Liu Xiangchun Liu XiaoBing Zhao |
| author_facet | Ke Chao Wei Song Sen Shao Dan Liu Xiangchun Liu XiaoBing Zhao |
| author_sort | Ke Chao |
| collection | DOAJ |
| description | Abstract Uneven lighting conditions often occur during real-life photography, such as images taken at night that may have both low-light dark areas and high-light overexposed areas. Traditional algorithms for enhancing low-light areas also increase the brightness of overexposed areas, affecting the overall visual effect of the image. Therefore, it is important to achieve differentiated enhancement of low-light and high-light areas. In this paper, we propose a network called correcting uneven illumination network (CUI-Net) with sparse attention transformer and convolutional neural network (CNN) to better extract low-light features by constraining high-light features. Specifically, CUI-Net consists of two main modules: a low-light enhancement module and an auxiliary module. The enhancement module is a hybrid network that combines the advantages of CNN and Transformer network, which can alleviate uneven lighting problems and enhance local details better. The auxiliary module is used to converge the enhancement results of multiple enhancement modules during the training phase, so that only one enhancement module is needed during the testing phase to speed up inference. Furthermore, zero-shot learning is used in this paper to adapt to complex uneven lighting environments without requiring paired or unpaired training data. Finally, to validate the effectiveness of the algorithm, we tested it on multiple datasets of different types, and the algorithm showed stable performance, demonstrating its good robustness. Additionally, by applying this algorithm to practical visual tasks such as object detection, face detection, and semantic segmentation, and comparing it with other state-of-the-art low-light image enhancement algorithms, we have demonstrated its practicality and advantages. |
| first_indexed | 2024-03-09T15:14:46Z |
| format | Article |
| id | doaj.art-8a6152f24f234aab830bbf19feb920b7 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-09T15:14:46Z |
| publishDate | 2023-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-8a6152f24f234aab830bbf19feb920b72023-11-26T13:11:20ZengNature PortfolioScientific Reports2045-23222023-08-0113111910.1038/s41598-023-39524-5CUI-Net: a correcting uneven illumination net for low-light image enhancementKe Chao0Wei Song1Sen Shao2Dan Liu3Xiangchun Liu4XiaoBing Zhao5School of Information Engineering, Minzu University of ChinaSchool of Information Engineering, Minzu University of ChinaSchool of Information Engineering, Minzu University of ChinaSchool of Information Engineering, Minzu University of ChinaSchool of Information Engineering, Minzu University of ChinaSchool of Information Engineering, Minzu University of ChinaAbstract Uneven lighting conditions often occur during real-life photography, such as images taken at night that may have both low-light dark areas and high-light overexposed areas. Traditional algorithms for enhancing low-light areas also increase the brightness of overexposed areas, affecting the overall visual effect of the image. Therefore, it is important to achieve differentiated enhancement of low-light and high-light areas. In this paper, we propose a network called correcting uneven illumination network (CUI-Net) with sparse attention transformer and convolutional neural network (CNN) to better extract low-light features by constraining high-light features. Specifically, CUI-Net consists of two main modules: a low-light enhancement module and an auxiliary module. The enhancement module is a hybrid network that combines the advantages of CNN and Transformer network, which can alleviate uneven lighting problems and enhance local details better. The auxiliary module is used to converge the enhancement results of multiple enhancement modules during the training phase, so that only one enhancement module is needed during the testing phase to speed up inference. Furthermore, zero-shot learning is used in this paper to adapt to complex uneven lighting environments without requiring paired or unpaired training data. Finally, to validate the effectiveness of the algorithm, we tested it on multiple datasets of different types, and the algorithm showed stable performance, demonstrating its good robustness. Additionally, by applying this algorithm to practical visual tasks such as object detection, face detection, and semantic segmentation, and comparing it with other state-of-the-art low-light image enhancement algorithms, we have demonstrated its practicality and advantages.https://doi.org/10.1038/s41598-023-39524-5 |
| spellingShingle | Ke Chao Wei Song Sen Shao Dan Liu Xiangchun Liu XiaoBing Zhao CUI-Net: a correcting uneven illumination net for low-light image enhancement Scientific Reports |
| title | CUI-Net: a correcting uneven illumination net for low-light image enhancement |
| title_full | CUI-Net: a correcting uneven illumination net for low-light image enhancement |
| title_fullStr | CUI-Net: a correcting uneven illumination net for low-light image enhancement |
| title_full_unstemmed | CUI-Net: a correcting uneven illumination net for low-light image enhancement |
| title_short | CUI-Net: a correcting uneven illumination net for low-light image enhancement |
| title_sort | cui net a correcting uneven illumination net for low light image enhancement |
| url | https://doi.org/10.1038/s41598-023-39524-5 |
| work_keys_str_mv | AT kechao cuinetacorrectingunevenilluminationnetforlowlightimageenhancement AT weisong cuinetacorrectingunevenilluminationnetforlowlightimageenhancement AT senshao cuinetacorrectingunevenilluminationnetforlowlightimageenhancement AT danliu cuinetacorrectingunevenilluminationnetforlowlightimageenhancement AT xiangchunliu cuinetacorrectingunevenilluminationnetforlowlightimageenhancement AT xiaobingzhao cuinetacorrectingunevenilluminationnetforlowlightimageenhancement |