DCENet-based low-light image enhancement improved by spiking encoding and convLSTM
The direct utilization of low-light images hinders downstream visual tasks. Traditional low-light image enhancement (LLIE) methods, such as Retinex-based networks, require image pairs. A spiking-coding methodology called intensity-to-latency has been used to gradually acquire the structural characte...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-03-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2024.1297671/full |
| _version_ | 1797277380845240320 |
|---|---|
| author | Xinghao Wang Qiang Wang Lei Zhang Yi Qu Fan Yi Jiayang Yu Qiuhan Liu Ruicong Xia Ziling Xu Sirong Tong |
| author_facet | Xinghao Wang Qiang Wang Lei Zhang Yi Qu Fan Yi Jiayang Yu Qiuhan Liu Ruicong Xia Ziling Xu Sirong Tong |
| author_sort | Xinghao Wang |
| collection | DOAJ |
| description | The direct utilization of low-light images hinders downstream visual tasks. Traditional low-light image enhancement (LLIE) methods, such as Retinex-based networks, require image pairs. A spiking-coding methodology called intensity-to-latency has been used to gradually acquire the structural characteristics of an image. convLSTM has been used to connect the features. This study introduces a simplified DCENet to achieve unsupervised LLIE as well as the spiking coding mode of a spiking neural network. It also applies the comprehensive coding features of convLSTM to improve the subjective and objective effects of LLIE. In the ablation experiment for the proposed structure, the convLSTM structure was replaced by a convolutional neural network, and the classical CBAM attention was introduced for comparison. Five objective evaluation metrics were compared with nine LLIE methods that currently exhibit strong comprehensive performance, with PSNR, SSIM, MSE, UQI, and VIFP exceeding the second place at 4.4% (0.8%), 3.9% (17.2%), 0% (15%), 0.1% (0.2%), and 4.3% (0.9%) on the LOL and SCIE datasets. Further experiments of the user study in five non-reference datasets were conducted to subjectively evaluate the effects depicted in the images. These experiments verified the remarkable performance of the proposed method. |
| first_indexed | 2024-03-07T15:47:45Z |
| format | Article |
| id | doaj.art-ace7382a381d494e876ab81c3dddff04 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-03-07T15:47:45Z |
| publishDate | 2024-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-ace7382a381d494e876ab81c3dddff042024-03-05T04:19:17ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2024-03-011810.3389/fnins.2024.12976711297671DCENet-based low-light image enhancement improved by spiking encoding and convLSTMXinghao WangQiang WangLei ZhangYi QuFan YiJiayang YuQiuhan LiuRuicong XiaZiling XuSirong TongThe direct utilization of low-light images hinders downstream visual tasks. Traditional low-light image enhancement (LLIE) methods, such as Retinex-based networks, require image pairs. A spiking-coding methodology called intensity-to-latency has been used to gradually acquire the structural characteristics of an image. convLSTM has been used to connect the features. This study introduces a simplified DCENet to achieve unsupervised LLIE as well as the spiking coding mode of a spiking neural network. It also applies the comprehensive coding features of convLSTM to improve the subjective and objective effects of LLIE. In the ablation experiment for the proposed structure, the convLSTM structure was replaced by a convolutional neural network, and the classical CBAM attention was introduced for comparison. Five objective evaluation metrics were compared with nine LLIE methods that currently exhibit strong comprehensive performance, with PSNR, SSIM, MSE, UQI, and VIFP exceeding the second place at 4.4% (0.8%), 3.9% (17.2%), 0% (15%), 0.1% (0.2%), and 4.3% (0.9%) on the LOL and SCIE datasets. Further experiments of the user study in five non-reference datasets were conducted to subjectively evaluate the effects depicted in the images. These experiments verified the remarkable performance of the proposed method.https://www.frontiersin.org/articles/10.3389/fnins.2024.1297671/fullintensity-to-latencyspiking encodinglow-light enhancementunpaired imagedeep learning |
| spellingShingle | Xinghao Wang Qiang Wang Lei Zhang Yi Qu Fan Yi Jiayang Yu Qiuhan Liu Ruicong Xia Ziling Xu Sirong Tong DCENet-based low-light image enhancement improved by spiking encoding and convLSTM Frontiers in Neuroscience intensity-to-latency spiking encoding low-light enhancement unpaired image deep learning |
| title | DCENet-based low-light image enhancement improved by spiking encoding and convLSTM |
| title_full | DCENet-based low-light image enhancement improved by spiking encoding and convLSTM |
| title_fullStr | DCENet-based low-light image enhancement improved by spiking encoding and convLSTM |
| title_full_unstemmed | DCENet-based low-light image enhancement improved by spiking encoding and convLSTM |
| title_short | DCENet-based low-light image enhancement improved by spiking encoding and convLSTM |
| title_sort | dcenet based low light image enhancement improved by spiking encoding and convlstm |
| topic | intensity-to-latency spiking encoding low-light enhancement unpaired image deep learning |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2024.1297671/full |
| work_keys_str_mv | AT xinghaowang dcenetbasedlowlightimageenhancementimprovedbyspikingencodingandconvlstm AT qiangwang dcenetbasedlowlightimageenhancementimprovedbyspikingencodingandconvlstm AT leizhang dcenetbasedlowlightimageenhancementimprovedbyspikingencodingandconvlstm AT yiqu dcenetbasedlowlightimageenhancementimprovedbyspikingencodingandconvlstm AT fanyi dcenetbasedlowlightimageenhancementimprovedbyspikingencodingandconvlstm AT jiayangyu dcenetbasedlowlightimageenhancementimprovedbyspikingencodingandconvlstm AT qiuhanliu dcenetbasedlowlightimageenhancementimprovedbyspikingencodingandconvlstm AT ruicongxia dcenetbasedlowlightimageenhancementimprovedbyspikingencodingandconvlstm AT zilingxu dcenetbasedlowlightimageenhancementimprovedbyspikingencodingandconvlstm AT sirongtong dcenetbasedlowlightimageenhancementimprovedbyspikingencodingandconvlstm |