Cargando…
Low-light image enhancement via adaptive frequency decomposition network
Images captured in low light conditions suffer from low visibility, blurred details and strong noise, resulting in unpleasant visual appearance and poor performance of high level visual tasks. To address these problems, existing approaches have attempted to enhance the visibility of low-light images...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10465598/ https://www.ncbi.nlm.nih.gov/pubmed/37644042 http://dx.doi.org/10.1038/s41598-023-40899-8 |
_version_ | 1785098704004317184 |
---|---|
author | Liang, Xiwen Chen, Xiaoyan Ren, Keying Miao, Xia Chen, Zhihui Jin, Yutao |
author_facet | Liang, Xiwen Chen, Xiaoyan Ren, Keying Miao, Xia Chen, Zhihui Jin, Yutao |
author_sort | Liang, Xiwen |
collection | PubMed |
description | Images captured in low light conditions suffer from low visibility, blurred details and strong noise, resulting in unpleasant visual appearance and poor performance of high level visual tasks. To address these problems, existing approaches have attempted to enhance the visibility of low-light images using convolutional neural networks (CNN). However, due to the insufficient consideration of the characteristics of the information of different frequency layers in the image, most of them yield blurry details and amplified noise. In this work, to fully extract and utilize these information, we proposed a novel Adaptive Frequency Decomposition Network (AFDNet) for low-light image enhancement. An Adaptive Frequency Decomposition (AFD) module is designed to adaptively extract low and high frequency information of different granularities. Specifically, the low-frequency information is employed for contrast enhancement and noise suppression in low-scale space and high-frequency information is for detail restoration in high-scale space. Meanwhile, a new frequency loss function are proposed to guarantee AFDNet’s recovery capability for different frequency information. Extensive experiments on various publicly available datasets show that AFDNet outperforms the existing state-of-the-art methods both quantitatively and visually. In addition, our results showed that the performance of the face detection can be effectively improved by using AFDNet as pre-processing. |
format | Online Article Text |
id | pubmed-10465598 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Nature Publishing Group UK |
record_format | MEDLINE/PubMed |
spelling | pubmed-104655982023-08-31 Low-light image enhancement via adaptive frequency decomposition network Liang, Xiwen Chen, Xiaoyan Ren, Keying Miao, Xia Chen, Zhihui Jin, Yutao Sci Rep Article Images captured in low light conditions suffer from low visibility, blurred details and strong noise, resulting in unpleasant visual appearance and poor performance of high level visual tasks. To address these problems, existing approaches have attempted to enhance the visibility of low-light images using convolutional neural networks (CNN). However, due to the insufficient consideration of the characteristics of the information of different frequency layers in the image, most of them yield blurry details and amplified noise. In this work, to fully extract and utilize these information, we proposed a novel Adaptive Frequency Decomposition Network (AFDNet) for low-light image enhancement. An Adaptive Frequency Decomposition (AFD) module is designed to adaptively extract low and high frequency information of different granularities. Specifically, the low-frequency information is employed for contrast enhancement and noise suppression in low-scale space and high-frequency information is for detail restoration in high-scale space. Meanwhile, a new frequency loss function are proposed to guarantee AFDNet’s recovery capability for different frequency information. Extensive experiments on various publicly available datasets show that AFDNet outperforms the existing state-of-the-art methods both quantitatively and visually. In addition, our results showed that the performance of the face detection can be effectively improved by using AFDNet as pre-processing. Nature Publishing Group UK 2023-08-29 /pmc/articles/PMC10465598/ /pubmed/37644042 http://dx.doi.org/10.1038/s41598-023-40899-8 Text en © The Author(s) 2023 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) . |
spellingShingle | Article Liang, Xiwen Chen, Xiaoyan Ren, Keying Miao, Xia Chen, Zhihui Jin, Yutao Low-light image enhancement via adaptive frequency decomposition network |
title | Low-light image enhancement via adaptive frequency decomposition network |
title_full | Low-light image enhancement via adaptive frequency decomposition network |
title_fullStr | Low-light image enhancement via adaptive frequency decomposition network |
title_full_unstemmed | Low-light image enhancement via adaptive frequency decomposition network |
title_short | Low-light image enhancement via adaptive frequency decomposition network |
title_sort | low-light image enhancement via adaptive frequency decomposition network |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10465598/ https://www.ncbi.nlm.nih.gov/pubmed/37644042 http://dx.doi.org/10.1038/s41598-023-40899-8 |
work_keys_str_mv | AT liangxiwen lowlightimageenhancementviaadaptivefrequencydecompositionnetwork AT chenxiaoyan lowlightimageenhancementviaadaptivefrequencydecompositionnetwork AT renkeying lowlightimageenhancementviaadaptivefrequencydecompositionnetwork AT miaoxia lowlightimageenhancementviaadaptivefrequencydecompositionnetwork AT chenzhihui lowlightimageenhancementviaadaptivefrequencydecompositionnetwork AT jinyutao lowlightimageenhancementviaadaptivefrequencydecompositionnetwork |