扬州做网站的公司,企业网站自己可以做吗,重庆会计之家是谁做的网站,网站设计网上培训学校本文介绍
在增强低光图像时#xff0c;许多深度学习算法基于Retinex理论。然而#xff0c;Retinex模型并没有考虑到暗部隐藏的损坏或者由光照过程引入的影响。此外#xff0c;这些方法通常需要繁琐的多阶段训练流程#xff0c;并依赖于卷积神经网络#xff0c;在捕捉长距…本文介绍
在增强低光图像时许多深度学习算法基于Retinex理论。然而Retinex模型并没有考虑到暗部隐藏的损坏或者由光照过程引入的影响。此外这些方法通常需要繁琐的多阶段训练流程并依赖于卷积神经网络在捕捉长距离依赖关系方面存在局限性。
本文提出了一种简单而又有原则性的单阶段Retinex-based框架ORF。ORF首先估计照明信息来点亮低光图像然后恢复损坏以生成增强的图像。我们设计了一个基于照明指导的TransformerIGT利用照明表示来指导不同光照条件下区域之间的非局部交互建模。将IGT插入到ORF中我们得到了我们的算法Retinexformer。
全面的定量和定性实验证明了我们的Retinexformer在13个基准测试上明显优于现有的方法。通过用户研究和在低光物体检测上的应用也揭示了我们方法的潜在实际价值。
结果展示 上图可以看出图像低照度增强显著增强了目标检测的recall值以及置信度因此图像增强对目标检测、目标跟踪等计算机视觉领域有重要意义。
代码运行
1. 创建环境
创建Conda环境
conda create -n Retinexformer python3.7
conda activate Retinexformer安装依赖项
conda install pytorch1.11 torchvision cudatoolkit11.3 -c pytorch
pip install matplotlib scikit-learn scikit-image opencv-python yacs joblib natsort h5py tqdm tensorboard
pip install einops gdown addict future lmdb numpy pyyaml requests scipy yapf lpips安装BasicSR
python setup.py develop --no_cuda_ext以上是创建和配置Retinexformer环境的步骤。首先使用Conda创建一个名为Retinexformer的环境并激活该环境。然后通过conda和pip安装所需的依赖项包括PyTorch、matplotlib、scikit-learn等。最后使用python命令运行setup.py文件来安装BasicSR。完成这些步骤后即可进入Retinexformer环境并开始使用。 2. 准备数据集
下载以下数据集
LOL-v1 百度网盘 (提取码: cyh2), 谷歌网盘
LOL-v2 百度网盘 (提取码: cyh2), 谷歌网盘
SID 百度网盘 (提取码: gplv), 谷歌网盘
SMID 百度网盘 (提取码: btux), 谷歌网盘
SDSD-indoor 百度网盘 (提取码: jo1v), 谷歌网盘
SDSD-outdoor 百度网盘 (提取码: uibk), 谷歌网盘
MIT-Adobe FiveK 百度网盘 (提取码:cyh2), 谷歌网盘, 官方网站
请按照sRGB设置处理MIT Adobe FiveK数据集。
然后按照以下方式组织这些数据集 |--data | |--LOLv1| | |--Train| | | |--input| | | | |--100.png| | | | |--101.png| | | | ...| | | |--target| | | | |--100.png| | | | |--101.png| | | | ...| | |--Test| | | |--input| | | | |--111.png| | | | |--146.png| | | | ...| | | |--target| | | | |--111.png| | | | |--146.png| | | | ...| |--LOLv2| | |--Real_captured| | | |--Train| | | | |--Low| | | | | |--00001.png| | | | | |--00002.png| | | | | ...| | | | |--Normal| | | | | |--00001.png| | | | | |--00002.png| | | | | ...| | | |--Test| | | | |--Low| | | | | |--00690.png| | | | | |--00691.png| | | | | ...| | | | |--Normal| | | | | |--00690.png| | | | | |--00691.png| | | | | ...| | |--Synthetic| | | |--Train| | | | |--Low| | | | | |--r000da54ft.png| | | | | |--r02e1abe2t.png| | | | | ...| | | | |--Normal| | | | | |--r000da54ft.png| | | | | |--r02e1abe2t.png| | | | | ...| | | |--Test| | | | |--Low| | | | | |--r00816405t.png| | | | | |--r02189767t.png| | | | | ...| | | | |--Normal| | | | | |--r00816405t.png| | | | | |--r02189767t.png| | | | | ...| |--SDSD| | |--indoor_static_np| | | |--input| | | | |--pair1| | | | | |--0001.npy| | | | | |--0002.npy| | | | | ...| | | | |--pair2| | | | | |--0001.npy| | | | | |--0002.npy| | | | | ...| | | | ...| | | |--GT| | | | |--pair1| | | | | |--0001.npy| | | | | |--0002.npy| | | | | ...| | | | |--pair2| | | | | |--0001.npy| | | | | |--0002.npy| | | | | ...| | | | ...| | |--outdoor_static_np| | | |--input| | | | |--MVI_0898| | | | | |--0001.npy| | | | | |--0002.npy| | | | | ...| | | | |--MVI_0918| | | | | |--0001.npy| | | | | |--0002.npy| | | | | ...| | | | ...| | | |--GT| | | | |--MVI_0898| | | | | |--0001.npy| | | | | |--0002.npy| | | | | ...| | | | |--MVI_0918| | | | | |--0001.npy| | | | | |--0002.npy| | | | | ...| | | | ...| |--SID| | |--short_sid2| | | |--00001| | | | |--00001_00_0.04s.npy| | | | |--00001_00_0.1s.npy| | | | |--00001_01_0.04s.npy| | | | |--00001_01_0.1s.npy| | | | ...| | | |--00002| | | | |--00002_00_0.04s.npy| | | | |--00002_00_0.1s.npy| | | | |--00002_01_0.04s.npy| | | | |--00002_01_0.1s.npy| | | | ...| | | ...| | |--long_sid2| | | |--00001| | | | |--00001_00_0.04s.npy| | | | |--00001_00_0.1s.npy| | | | |--00001_01_0.04s.npy| | | | |--00001_01_0.1s.npy| | | | ...| | | |--00002| | | | |--00002_00_0.04s.npy| | | | |--00002_00_0.1s.npy| | | | |--00002_01_0.04s.npy| | | | |--00002_01_0.1s.npy| | | | ...| | | ...| |--SMID| | |--SMID_LQ_np| | | |--0001| | | | |--0001.npy| | | | |--0002.npy| | | | ...| | | |--0002| | | | |--0001.npy| | | | |--0002.npy| | | | ...| | | ...| | |--SMID_Long_np| | | |--0001| | | | |--0001.npy| | | | |--0002.npy| | | | ...| | | |--0002| | | | |--0001.npy| | | | |--0002.npy| | | | ...| | | ...| |--FiveK| | |--train| | | |--input| | | | |--a0099-kme_264.jpg| | | | |--a0101-kme_610.jpg| | | | ...| | | |--target| | | | |--a0099-kme_264.jpg| | | | |--a0101-kme_610.jpg| | | | ...| | |--test| | | |--input| | | | |--a4574-DSC_0038.jpg| | | | |--a4576-DSC_0217.jpg| | | | ...| | | |--target| | | | |--a4574-DSC_0038.jpg| | | | |--a4576-DSC_0217.jpg| | | | ...3 测试
下载我们的模型文件从百度网盘 (提取码: cyh2) 或 谷歌网盘然后将它们放在名为 pretrained_weights 的文件夹中。
下面是测试命令的示例
# LOL-v1
python3 Enhancement/test_from_dataset.py --opt Options/RetinexFormer_LOL_v1.yml --weights pretrained_weights/LOL_v1.pth --dataset LOL_v1# LOL-v2-real
python3 Enhancement/test_from_dataset.py --opt Options/RetinexFormer_LOL_v2_real.yml --weights pretrained_weights/LOL_v2_real.pth --dataset LOL_v2_real# LOL-v2-synthetic
python3 Enhancement/test_from_dataset.py --opt Options/RetinexFormer_LOL_v2_synthetic.yml --weights pretrained_weights/LOL_v2_synthetic.pth --dataset LOL_v2_synthetic# SID
python3 Enhancement/test_from_dataset.py --opt Options/RetinexFormer_SID.yml --weights pretrained_weights/SID.pth --dataset SID# SMID
python3 Enhancement/test_from_dataset.py --opt Options/RetinexFormer_SMID.yml --weights pretrained_weights/SMID.pth --dataset SMID# SDSD-indoor
python3 Enhancement/test_from_dataset.py --opt Options/RetinexFormer_SDSD_indoor.yml --weights pretrained_weights/SDSD_indoor.pth --dataset SDSD_indoor# SDSD-outdoor
python3 Enhancement/test_from_dataset.py --opt Options/RetinexFormer_SDSD_outdoor.yml --weights pretrained_weights/SDSD_outdoor.pth --dataset SDSD_outdoor# FiveK
python3 Enhancement/test_from_dataset.py --opt Options/RetinexFormer_FiveK.yml --weights pretrained_weights/FiveK.pth --dataset FiveK4 训练
# LOL-v1
python3 basicsr/train.py --opt Options/RetinexFormer_LOL_v1.yml# LOL-v2-real-
python3 basicsr/train.py --opt Options/RetinexFormer_LOL_v2_real.yml# LOL-v2-synthetic
python3 basicsr/train.py --opt Options/RetinexFormer_LOL_v2_synthetic.yml# SID1. Create Envirement
Make Conda Environment
conda create -n Retinexformer python3.7
conda activate Retinexformer
Install Dependencies
conda install pytorch1.11 torchvision cudatoolkit11.3 -c pytorch
pip install matplotlib scikit-learn scikit-image opencv-python yacs joblib natsort h5py tqdm tensorboard
pip install einops gdown addict future lmdb numpy pyyaml requests scipy yapf lpips
Install BasicSR
python setup.py develop --no_cuda_ext
nbsp;2. Prepare Dataset
Download the following datasets:LOL-v1 Baidu Disk (code: cyh2), Google DriveLOL-v2 Baidu Disk (code: cyh2), Google DriveSID Baidu Disk (code: gplv), Google DriveSMID Baidu Disk (code: btux), Google DriveSDSD-indoor Baidu Disk (code: jo1v), Google DriveSDSD-outdoor Baidu Disk (code: uibk), Google DriveMIT-Adobe FiveK Baidu Disk (code:cyh2), Google Drive, OfficialPlease process the MIT Adobe FiveK dataset following the sRGB setting
Then organize these datasets as follows:
|--data | |--LOLv1| | |--Train| | | |--input| | | | |--100.png| | | | |--101.png| | | | ...| | | |--target| | | | |--100.png| | | | |--101.png| | | | ...| | |--Test| | | |--input| | | | |--111.png| | | | |--146.png| | | | ...| | | |--target| | | | |--111.png| | | | |--146.png| | | | ...| |--LOLv2| | |--Real_captured| | | |--Train| | | | |--Low| | | | | |--00001.png| | | | | |--00002.png| | | | | ...| | | | |--Normal| | | | | |--00001.png| | | | | |--00002.png| | | | | ...| | | |--Test| | | | |--Low| | | | | |--00690.png| | | | | |--00691.png| | | | | ...| | | | |--Normal| | | | | |--00690.png| | | | | |--00691.png| | | | | ...| | |--Synthetic| | | |--Train| | | | |--Low| | | | | |--r000da54ft.png| | | | | |--r02e1abe2t.png| | | | | ...| | | | |--Normal| | | | | |--r000da54ft.png| | | | | |--r02e1abe2t.png| | | | | ...| | | |--Test| | | | |--Low| | | | | |--r00816405t.png| | | | | |--r02189767t.png| | | | | ...| | | | |--Normal| | | | | |--r00816405t.png| | | | | |--r02189767t.png| | | | | ...| |--SDSD| | |--indoor_static_np| | | |--input| | | | |--pair1| | | | | |--0001.npy| | | | | |--0002.npy| | | | | ...| | | | |--pair2| | | | | |--0001.npy| | | | | |--0002.npy| | | | | ...| | | | ...| | | |--GT| | | | |--pair1| | | | | |--0001.npy| | | | | |--0002.npy| | | | | ...| | | | |--pair2| | | | | |--0001.npy| | | | | |--0002.npy| | | | | ...| | | | ...| | |--outdoor_static_np| | | |--input| | | | |--MVI_0898| | | | | |--0001.npy| | | | | |--0002.npy| | | | | ...| | | | |--MVI_0918| | | | | |--0001.npy| | | | | |--0002.npy| | | | | ...| | | | ...| | | |--GT| | | | |--MVI_0898| | | | | |--0001.npy| | | | | |--0002.npy| | | | | ...| | | | |--MVI_0918| | | | | |--0001.npy| | | | | |--0002.npy| | | | | ...| | | | ...| |--SID| | |--short_sid2| | | |--00001| | | | |--00001_00_0.04s.npy| | | | |--00001_00_0.1s.npy| | | | |--00001_01_0.04s.npy| | | | |--00001_01_0.1s.npy| | | | ...| | | |--00002| | | | |--00002_00_0.04s.npy| | | | |--00002_00_0.1s.npy| | | | |--00002_01_0.04s.npy| | | | |--00002_01_0.1s.npy| | | | ...| | | ...| | |--long_sid2| | | |--00001| | | | |--00001_00_0.04s.npy| | | | |--00001_00_0.1s.npy| | | | |--00001_01_0.04s.npy| | | | |--00001_01_0.1s.npy| | | | ...| | | |--00002| | | | |--00002_00_0.04s.npy| | | | |--00002_00_0.1s.npy| | | | |--00002_01_0.04s.npy| | | | |--00002_01_0.1s.npy| | | | ...| | | ...| |--SMID| | |--SMID_LQ_np| | | |--0001| | | | |--0001.npy| | | | |--0002.npy| | | | ...| | | |--0002| | | | |--0001.npy| | | | |--0002.npy| | | | ...| | | ...| | |--SMID_Long_np| | | |--0001| | | | |--0001.npy| | | | |--0002.npy| | | | ...| | | |--0002| | | | |--0001.npy| | | | |--0002.npy| | | | ...| | | ...| |--FiveK| | |--train| | | |--input| | | | |--a0099-kme_264.jpg| | | | |--a0101-kme_610.jpg| | | | ...| | | |--target| | | | |--a0099-kme_264.jpg| | | | |--a0101-kme_610.jpg| | | | ...| | |--test| | | |--input| | | | |--a4574-DSC_0038.jpg| | | | |--a4576-DSC_0217.jpg| | | | ...| | | |--target| | | | |--a4574-DSC_0038.jpg| | | | |--a4576-DSC_0217.jpg| | | | ...
/detailsWe also provide download links for LIME, NPE, MEF, DICM, and VV datasets that have no ground truth:Baidu Disk (code: cyh2)or Google Drivenbsp; 3. Testing
Download our models from Baidu Disk (code: cyh2) or Google Drive. Put them in folder pretrained_weights
# LOL-v1
python3 Enhancement/test_from_dataset.py --opt Options/RetinexFormer_LOL_v1.yml --weights pretrained_weights/LOL_v1.pth --dataset LOL_v1
# LOL-v2-real
python3 Enhancement/test_from_dataset.py --opt Options/RetinexFormer_LOL_v2_real.yml --weights pretrained_weights/LOL_v2_real.pth --dataset LOL_v2_real
# LOL-v2-synthetic
python3 Enhancement/test_from_dataset.py --opt Options/RetinexFormer_LOL_v2_synthetic.yml --weights pretrained_weights/LOL_v2_synthetic.pth --dataset LOL_v2_synthetic
# SID
python3 Enhancement/test_from_dataset.py --opt Options/RetinexFormer_SID.yml --weights pretrained_weights/SID.pth --dataset SID
# SMID
python3 Enhancement/test_from_dataset.py --opt Options/RetinexFormer_SMID.yml --weights pretrained_weights/SMID.pth --dataset SMID
# SDSD-indoor
python3 Enhancement/test_from_dataset.py --opt Options/RetinexFormer_SDSD_indoor.yml --weights pretrained_weights/SDSD_indoor.pth --dataset SDSD_indoor
# SDSD-outdoor
python3 Enhancement/test_from_dataset.py --opt Options/RetinexFormer_SDSD_outdoor.yml --weights pretrained_weights/SDSD_outdoor.pth --dataset SDSD_outdoor
# FiveK
python3 Enhancement/test_from_dataset.py --opt Options/RetinexFormer_FiveK.yml --weights pretrained_weights/FiveK.pth --dataset FiveK
nbsp;4. Training
Feel free to check our training logs from Baidu Disk (code: cyh2) or Google Drivepython3 basicsr/train.py --opt Options/RetinexFormer_SID.yml# SMID
python3 basicsr/train.py --opt Options/RetinexFormer_SMID.yml# SDSD-indoor
python3 basicsr/train.py --opt Options/RetinexFormer_SDSD_indoor.yml# SDSD-outdoorxunlian
python3 basicsr/train.py --opt Options/RetinexFormer_SDSD_outdoor.yml
在增强低光图像时许多深度学习算法基于Retinex理论。然而Retinex模型并没有考虑到暗部隐藏的损坏或者由光照过程引入的影响。此外这些方法通常需要繁琐的多阶段训练流程并依赖于卷积神经网络在捕捉长距离依赖关系方面存在局限性。本文提出了一种简单而又有原则性的单阶段Retinex-based框架ORF。ORF首先估计照明信息来点亮低光图像然后恢复损坏以生成增强的图像。我们设计了一个基于照明指导的TransformerIGT利用照明表示来指导不同光照条件下区域之间的非局部交互建模。将IGT插入到ORF中我们得到了我们的算法Retinexformer。全面的定量和定性实验证明了我们的Retinexformer在13个基准测试上明显优于现有的方法。通过用户研究和在低光物体检测上的应用也揭示了我们方法的潜在实际价值。
# FiveK
python3 basicsr/train.py --opt Options/RetinexFormer_FiveK.yml5 图像评价指标对比
