Removing rain from a single image is a challenging task due to the absence of temporal information. Considering that a rainy image can be decomposed into the low-frequency(LF) and high-frequency(HF) components, where ...Removing rain from a single image is a challenging task due to the absence of temporal information. Considering that a rainy image can be decomposed into the low-frequency(LF) and high-frequency(HF) components, where the coarse scale information is retained in the LF component and the rain streaks and texture correspond to the HF component, we propose a single image rain removal algorithm using image decomposition and a dense network. We design two task-driven sub-networks to estimate the LF and non-rain HF components of a rainy image. The high-frequency estimation sub-network employs a densely connected network structure, while the low-frequency sub-network uses a simple convolutional neural network(CNN).We add total variation(TV) regularization and LF-channel fidelity terms to the loss function to optimize the two subnetworks jointly. The method then obtains de-rained output by combining the estimated LF and non-rain HF components.Extensive experiments on synthetic and real-world rainy images demonstrate that our method removes rain streaks while preserving non-rain details, and achieves superior de-raining performance both perceptually and quantitatively.展开更多
提出了一种基于全变分正则与L_(2,1)范数的视频去雨张量模型用于解决雨线遮挡问题。首先,对雨线成分与视频背景先验信息进行预处理,获取相应正则化条件的构建依据以增强各部分稀疏性,便于促进雨线分离。其次,考虑到视频图像存在不规则...提出了一种基于全变分正则与L_(2,1)范数的视频去雨张量模型用于解决雨线遮挡问题。首先,对雨线成分与视频背景先验信息进行预处理,获取相应正则化条件的构建依据以增强各部分稀疏性,便于促进雨线分离。其次,考虑到视频图像存在不规则动态对象,引入全变分正则项来抑制背景强度变化,缓解雨线的误判现象。采用交替方向乘子法(alternating direction method of multipliers,ADMM)可以有效地对所提出的张量模型进行求解,并在合成数据与真实数据集上开展大量实验。结果表明,所提方法在动态背景情况下有效去除视频图像雨线的同时,保留了更多背景细节信息。与相关先进方法相比,所提方法在峰值信噪比、结构相似性和残差三种综合性能量化指标上均具有较大的优势。展开更多
目的雨天户外采集的图像常常因为雨线覆盖图像信息产生色变和模糊现象。为了提高雨天图像的质量,本文提出一种基于自适应选择卷积网络深度学习的单幅图像去雨算法。方法针对雨图中背景误判和雨痕残留问题,加入网络训练的雨线修正系数(re...目的雨天户外采集的图像常常因为雨线覆盖图像信息产生色变和模糊现象。为了提高雨天图像的质量,本文提出一种基于自适应选择卷积网络深度学习的单幅图像去雨算法。方法针对雨图中背景误判和雨痕残留问题,加入网络训练的雨线修正系数(refine factor,RF),改进现有雨图模型,更精确地描述雨图中各像素受到雨线的影响。构建选择卷积网络(selective kernel network,SK Net),自适应地选择不同卷积核对应维度的信息,进一步学习、融合不同卷积核的信息,提高网络的表达力,最后构建包含SK Net、refine factor net和residual net子网络的自适应卷积残差修正网络(selective kernel convolution using a residual refine factor,SKRF),直接学习雨线图和残差修正系数(RF),减少映射区间,减少背景误判。结果实验通过设计的SKRF网络,在公开的Rain12测试集上进行去雨实验,取得了比现有方法更高的精确度,峰值信噪比(peak signal to noise ratio,PSNR)达到34.62 d B,结构相似性(structural similarity,SSIM)达到0.9706。表明SKRF网络对单幅图像去雨效果有明显优势。结论单幅图像去雨SKRF算法为雨图模型中的雨线图提供一个额外的修正残差系数,以降低学习映射区间,自适应选择卷积网络模型提升雨图模型的表达力和兼容性。展开更多
基金supported by the National Natural Science Foundation of China(61471313)the Natural Science Foundation of Hebei Province(F2019203318)
文摘Removing rain from a single image is a challenging task due to the absence of temporal information. Considering that a rainy image can be decomposed into the low-frequency(LF) and high-frequency(HF) components, where the coarse scale information is retained in the LF component and the rain streaks and texture correspond to the HF component, we propose a single image rain removal algorithm using image decomposition and a dense network. We design two task-driven sub-networks to estimate the LF and non-rain HF components of a rainy image. The high-frequency estimation sub-network employs a densely connected network structure, while the low-frequency sub-network uses a simple convolutional neural network(CNN).We add total variation(TV) regularization and LF-channel fidelity terms to the loss function to optimize the two subnetworks jointly. The method then obtains de-rained output by combining the estimated LF and non-rain HF components.Extensive experiments on synthetic and real-world rainy images demonstrate that our method removes rain streaks while preserving non-rain details, and achieves superior de-raining performance both perceptually and quantitatively.
文摘提出了一种基于全变分正则与L_(2,1)范数的视频去雨张量模型用于解决雨线遮挡问题。首先,对雨线成分与视频背景先验信息进行预处理,获取相应正则化条件的构建依据以增强各部分稀疏性,便于促进雨线分离。其次,考虑到视频图像存在不规则动态对象,引入全变分正则项来抑制背景强度变化,缓解雨线的误判现象。采用交替方向乘子法(alternating direction method of multipliers,ADMM)可以有效地对所提出的张量模型进行求解,并在合成数据与真实数据集上开展大量实验。结果表明,所提方法在动态背景情况下有效去除视频图像雨线的同时,保留了更多背景细节信息。与相关先进方法相比,所提方法在峰值信噪比、结构相似性和残差三种综合性能量化指标上均具有较大的优势。
文摘目的雨天户外采集的图像常常因为雨线覆盖图像信息产生色变和模糊现象。为了提高雨天图像的质量,本文提出一种基于自适应选择卷积网络深度学习的单幅图像去雨算法。方法针对雨图中背景误判和雨痕残留问题,加入网络训练的雨线修正系数(refine factor,RF),改进现有雨图模型,更精确地描述雨图中各像素受到雨线的影响。构建选择卷积网络(selective kernel network,SK Net),自适应地选择不同卷积核对应维度的信息,进一步学习、融合不同卷积核的信息,提高网络的表达力,最后构建包含SK Net、refine factor net和residual net子网络的自适应卷积残差修正网络(selective kernel convolution using a residual refine factor,SKRF),直接学习雨线图和残差修正系数(RF),减少映射区间,减少背景误判。结果实验通过设计的SKRF网络,在公开的Rain12测试集上进行去雨实验,取得了比现有方法更高的精确度,峰值信噪比(peak signal to noise ratio,PSNR)达到34.62 d B,结构相似性(structural similarity,SSIM)达到0.9706。表明SKRF网络对单幅图像去雨效果有明显优势。结论单幅图像去雨SKRF算法为雨图模型中的雨线图提供一个额外的修正残差系数,以降低学习映射区间,自适应选择卷积网络模型提升雨图模型的表达力和兼容性。
