Low-light image and video enhancement using deep learning: a survey
Low-light image enhancement (LLIE) aims at improving the perception or interpretability of an image captured in an environment with poor illumination. Recent advances in this area are dominated by deep learning-based solutions, where many learning strategies, network structures, loss functions, trai...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/170345 |
| _version_ | 1826126097328111616 |
|---|---|
| author | Li, Chongyi Guo, Chunle Han, Linghao Jiang, Jun Cheng, Ming-Ming Gu, Jinwei Loy, Chen Change |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Li, Chongyi Guo, Chunle Han, Linghao Jiang, Jun Cheng, Ming-Ming Gu, Jinwei Loy, Chen Change |
| author_sort | Li, Chongyi |
| collection | NTU |
| description | Low-light image enhancement (LLIE) aims at improving the perception or interpretability of an image captured in an environment with poor illumination. Recent advances in this area are dominated by deep learning-based solutions, where many learning strategies, network structures, loss functions, training data, etc. have been employed. In this paper, we provide a comprehensive survey to cover various aspects ranging from algorithm taxonomy to unsolved open issues. To examine the generalization of existing methods, we propose a low-light image and video dataset, in which the images and videos are taken by different mobile phones' cameras under diverse illumination conditions. Besides, for the first time, we provide a unified online platform that covers many popular LLIE methods, of which the results can be produced through a user-friendly web interface. In addition to qualitative and quantitative evaluation of existing methods on publicly available and our proposed datasets, we also validate their performance in face detection in the dark. This survey together with the proposed dataset and online platform could serve as a reference source for future study and promote the development of this research field. The proposed platform and dataset as well as the collected methods, datasets, and evaluation metrics are publicly available and will be regularly updated. Project page: https://www.mmlab-ntu.com/project/lliv_survey/index.html. |
| first_indexed | 2024-10-01T06:47:08Z |
| format | Journal Article |
| id | ntu-10356/170345 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:47:08Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1703452023-09-08T03:11:27Z Low-light image and video enhancement using deep learning: a survey Li, Chongyi Guo, Chunle Han, Linghao Jiang, Jun Cheng, Ming-Ming Gu, Jinwei Loy, Chen Change School of Computer Science and Engineering S-Lab Engineering::Computer science and engineering Computational Photography Deep Learning Low-light image enhancement (LLIE) aims at improving the perception or interpretability of an image captured in an environment with poor illumination. Recent advances in this area are dominated by deep learning-based solutions, where many learning strategies, network structures, loss functions, training data, etc. have been employed. In this paper, we provide a comprehensive survey to cover various aspects ranging from algorithm taxonomy to unsolved open issues. To examine the generalization of existing methods, we propose a low-light image and video dataset, in which the images and videos are taken by different mobile phones' cameras under diverse illumination conditions. Besides, for the first time, we provide a unified online platform that covers many popular LLIE methods, of which the results can be produced through a user-friendly web interface. In addition to qualitative and quantitative evaluation of existing methods on publicly available and our proposed datasets, we also validate their performance in face detection in the dark. This survey together with the proposed dataset and online platform could serve as a reference source for future study and promote the development of this research field. The proposed platform and dataset as well as the collected methods, datasets, and evaluation metrics are publicly available and will be regularly updated. Project page: https://www.mmlab-ntu.com/project/lliv_survey/index.html. Agency for Science, Technology and Research (A*STAR) Nanyang Technological University This work was supported under the RIE2020 Industry Alignment Fund Industry Collaboration Projects (IAF-ICP) Funding Initiative, as well as cash and in-kind contribution from the industry partner(s). It was also partially supported by the NTU SUG and NAP grant. Chunle Guo is sponsored by CAAI-Huawei MindSpore Open Fund. 2023-09-08T03:11:26Z 2023-09-08T03:11:26Z 2021 Journal Article Li, C., Guo, C., Han, L., Jiang, J., Cheng, M., Gu, J. & Loy, C. C. (2021). Low-light image and video enhancement using deep learning: a survey. IEEE Transactions On Pattern Analysis and Machine Intelligence, 44(12), 9396-9416. https://dx.doi.org/10.1109/TPAMI.2021.3126387 0162-8828 https://hdl.handle.net/10356/170345 10.1109/TPAMI.2021.3126387 34752382 2-s2.0-85141891287 12 44 9396 9416 en IEEE Transactions on Pattern Analysis and Machine Intelligence © 2021 IEEE. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering Computational Photography Deep Learning Li, Chongyi Guo, Chunle Han, Linghao Jiang, Jun Cheng, Ming-Ming Gu, Jinwei Loy, Chen Change Low-light image and video enhancement using deep learning: a survey |
| title | Low-light image and video enhancement using deep learning: a survey |
| title_full | Low-light image and video enhancement using deep learning: a survey |
| title_fullStr | Low-light image and video enhancement using deep learning: a survey |
| title_full_unstemmed | Low-light image and video enhancement using deep learning: a survey |
| title_short | Low-light image and video enhancement using deep learning: a survey |
| title_sort | low light image and video enhancement using deep learning a survey |
| topic | Engineering::Computer science and engineering Computational Photography Deep Learning |
| url | https://hdl.handle.net/10356/170345 |
| work_keys_str_mv | AT lichongyi lowlightimageandvideoenhancementusingdeeplearningasurvey AT guochunle lowlightimageandvideoenhancementusingdeeplearningasurvey AT hanlinghao lowlightimageandvideoenhancementusingdeeplearningasurvey AT jiangjun lowlightimageandvideoenhancementusingdeeplearningasurvey AT chengmingming lowlightimageandvideoenhancementusingdeeplearningasurvey AT gujinwei lowlightimageandvideoenhancementusingdeeplearningasurvey AT loychenchange lowlightimageandvideoenhancementusingdeeplearningasurvey |