Single image dehazing using improved cycleGAN

Haze is an aggregation of very fine, widely dispersed, solid and/or liquid particles suspended in the atmosphere. In this paper, we propose an end-to-end network for single image dehazing, which enhances the CycleGAN model by introducing a transformer architecture within the generator, which is specific for haze removal. The proposed model is trained in an unpaired fashion with clear and hazy images altogether and does not require pairs of hazy and corresponding ground-truth clear images. Furthermore, the proposed model does not depend on estimating the parameters of the atmospheric scattering model. Rather, it uses a K-estimation module as the generator’s transformer for complete end-to-end modeling. The feature transformer introduced in the proposed generator model transforms the encoded features into desired feature space and then feeds them into the CycleGAN decoder to create a clear image. In the proposed model we further modified the cycle consistency loss to include the SSIM loss along with pixel-wise mean loss to produce a new loss function specific for the reconstruction task, which enhances the performance of the proposed model. The model performs well even on the high-resolution images provided in the NTIRE 2019 challenge dataset for single image dehazing. Further, we perform experiments on NYU-Depth and reside beta datasets. Results of our experiments show the efficacy of the proposed approach compared to the state-of-the-art in removing the haze from the input image.     

采用自适应全局亮度补偿的夜间去雾算法

针对夜间雾霾天气情况下还原的去雾图像存在颜色失真、纹理损失严重、去雾效果差等问题,本文提出了一种夜间去雾算法,采用自适应全局亮度补偿、同态滤波、限制对比度自适应直方图均衡化算法以及联合双边滤波对降质图像进行处理,结合大气散射模型得到还原的去雾图像。实验结果表明,该算法的夜间去雾效果好、处理速度快,较对比算法在对比度、平均梯度以及信息熵上均有改善,有效减少了还原图像的颜色失真、纹理损失。     

基于区间估计的单幅图像快速去雾

针对雾、霾等天气条件下捕获的图像存在严重降质现象,该文提出一种基于区间估计的单幅图像快速去雾方法。该方法从大气散射模型出发,基于暗通道先验理论,利用最小值滤波和灰度开运算,通过区间估计得到大气光值,同时得到介质传输率的初始估计值。通过对大气光照进行白平衡处理,从而得到简化大气散射模型。然后,利用简化大气散射模型和介质传输率的初始估计值,通过区间估计得到场景反照率的暗通道值,进一步得到介质传输率的粗略估计值。将介质传输率的初始估计值和粗略估计值进行像素级融合,通过联合双边滤波和值域调整得到介质传输率的最终估计值。最后,通过简化大气散射模型和色调调整得到去雾图像。实验结果表明,所提算法具有较快的运算速度,能有效提高去雾图像的清晰度和对比度,同时获得较好的色调保真度。     

Exploration of the Relation between Input Noise and Generated Image in Generative Adversarial Networks

In this paper, we propose a hybrid model aiming to map the input noise vector to the label of the generated image by the generative adversarial network (GAN). This model mainly consists of a pre-trained deep convolution generative adversarial network (DCGAN) and a classifier. By using the model, we visualize the distribution of two-dimensional input noise, leading to a specific type of the generated image after each training epoch of GAN. The visualization reveals the distribution feature of the input noise vector and the performance of the generator. With this feature, we try to build a guided generator (GG) with the ability to produce a fake image we need. Two methods are proposed to build GG. One is the most significant noise (MSN) method, and the other utilizes labeled noise. The MSN method can generate images precisely but with less variations. In contrast, the labeled noise method has more variations but is slightly less stable. Finally, we propose a criterion to measure the performance of the generator, which can be used as a loss function to effectively train the network.     

基于雾气特征与不等关系约束的去雾方法

针对现有去雾算法未充分考虑图像雾气信息、复原图像细节模糊等问题,提出一种新颖的反映图像雾信息分布的雾气特征图,并采用不等关系约束方法提高图像质量。首先,提取退化图像的极值通道以实现雾气信息的粗略估计,并通过L-1正则化对其进行优化从而得到雾气特征图。其次,提出一种基于雾气特征的初级大气光幕函数,通过对颜色通道和大气光幕作深入分析,利用均值不等式获得约束后的退化场景大气光幕。最后,利用雾气特征图对局部大气光进行改进,并基于大气散射模型实现图像去雾。将所提算法在真实雾图和合成数据集雾图上与其他经典方法进行比较分析,可以发现,所提算法在单幅图像去雾中展现了较好的性能,且在夜间雾图复原中更具优势。     

Efficient image dehazing algorithm using multiple priors constraints

In this study, a robust and efficient image dehazing technique based on the atmospheric scattering model is proposed, which effectively overcomes the limitations of a single prior condition. It is composed of a transmission estimation module and an atmospheric light estimation module. The transmission estimation module integrates multiple dehazing prior strategies and effectively optimises transmission estimation and application range. The atmospheric light estimation module uses the fuzzy C-means clustering algorithm (FCM) to estimate the atmospheric light of different scenes in an image. Unlike in the previous work, the atmospheric light in this module is a nonglobal value, and a pixel-level atmospheric light value matrix is obtained. Numerous experiments show that the proposed dehazing algorithm is superior to state-of-the-art methods.     

结合线性景深和自适应雾浓度的去雾算法

针对图像去雾中由于景深和大气光估计不准确等问题,导致军事监测、目标检测、导航、无人驾驶等系统成像设备获取到的图像质量下降,提出一种结合线性景深估计和自适应雾浓度估计的去雾算法。首先,依照景深与亮度分量和饱和度的关系,利用双滤波优化二者高亮区域,结合线性转换建立线性模型估计景深。然后,提取纹理特征构造雾浓度模型求取自适应散射系数,通过所求景深与自适应散射系数得到透射率。最后,根据对雾图是否含有天空区域的判决,采用两种不同的大气光估计方法。实验结果通过与不同去雾算法定性和定量分析,所提出的方法在保留深度边缘、颜色质量及细节方面具有良好的有效性和鲁棒性,图像恢复质量也相对较佳。     

一种联合雾线和凸优化的单幅图像去雾算法

为解决传统去雾算法容易在天空区域出现光晕效应和复原后的图像颜色过饱和等问题,提出了一种联合雾线和凸优化的单幅图像去雾算法。该算法使用雾线先验来估计大气光值,并通过离散小波变换构建了一个降维的子带雾图模型,进一步将双线性耦合项和大气光传输分布作为线性优化变量进行凸优化求解来得到透射率,最后通过大气散射模型恢复出无雾图像。实验结果表明该算法在大多数情况下恢复的图像清晰自然,与其他几种常用的图像去雾算法的客观对比,也证实了该算法的可行性和有效性。     

Weakly supervised single image dehazing

Single image dehazing is a critical image pre-processing step for many practical vision systems. Most existing dehazing methods solve this problem utilizing various of hand-crafted priors or by supervised training on the synthetic hazy image information (such as haze-free image, transmission map and atmospheric light). However, the assumptions on the hand-crafted priors are easily violated and collecting realistic transmission map and atmospheric light are unpractical. In this paper, we propose a novel weakly supervised network based on the multi-level multi-scale block. The proposed network reduces the constraint on the training data and automatically estimates the transmission map and the atmospheric light as well as the intermediate haze-free image without using any realistic transmission map and atmospheric light as supervision. Moreover, the estimated intermediate haze-free image helps to generate accurate transmission map and atmospheric light by embedding the physical-model, which presents reliable restoration of the final haze-free image. In particular, our network also can be trained on the real-world dataset to fine-tune the model and the fine-tuning operation improves the dehazing performance on the real-world dataset. Quantitative and qualitative experimental results demonstrate the proposed method performs on par with the supervised methods.     

结合区域生长与容差机制的暗通道去雾算法

针对传统的暗通道先验算法在处理带有大面积天空区域的有雾图像时出现明显的块效应、色彩失真和亮度偏低等问题,提出了一种结合区域生长与容差机制的去雾算法。首先通过灰度图腐蚀求出暗通道;接着利用种子区域生长法分割出天空区域,并把天空区域的平均灰度值作为大气光值估计;然后结合大气散射模型得到粗略的透视率,并采用改良的容差机制和引导滤波对透视率进行修正和细化;最后,引入Retinex法对图像进行后处理,进一步调整色彩和亮度。实验结果表明,本文提出的去雾算法对带有天空区域的图像去雾效果明显,天空区域的色彩有了显著改善,图像整体清晰明亮。     

基于大气散射模型的图像去雾及亮度增强算法

针对雾图能见度低和去雾图像亮度偏暗的问题,提出一种基于大气散射模型的双阶段去雾算法。首先使用线性变换估算复原图像亮度,使用拉伸方法估算复原图像饱和度,根据复原图像亮度、饱和度估算其最小通道,联合雾图最小通道获取粗糙透射率。在不同阶段分别使用双梯度代价函数、导向滤波优化粗糙透射率,依据大气散射模型复原图像和增强亮度。实验结果表明,所提算法复原图像更清晰明亮;图像综合质量、峰值信噪比和运行时间等客观指标均值优于所有比较算法,其中图像综合质量最少提高1.55倍,运行速度最少加速1.50倍。所提算法有效地增强了雾图的能见度和明亮度。     

基于暗通道先验的图像去雾优化算法

暗通道先验算法虽然在单幅图像去雾方面取得了一定的效果,但是该算法运行时间较长,另外对环境光的计算不太准确,不适用于天空区域,会导致复原图像色彩失真、亮度偏暗。针对这些缺陷,本文提出一种改进的White Patch Retinex算法,对原有图像去雾算法进行优化。首先,通过改进的White Patch Retinex算法计算出环境光。其次通过暗通道先验算法获得透射率。最后根据得到的环境光和透射率,求解大气散射模型,从而得到去雾后的图像。实验结果表明,该算法不仅运行时间较短,对分辨率为600×800的图像处理时间平均为5 s左右,且能解决天空区域失真问题,去雾后的图像具有较高的亮度和对比度。     

基于霾层学习的单幅图像去雾算法

针对传统去雾算法出现色彩失真、去雾不完全、出现光晕等现象,本文提出了一种基于霾层学习的卷积神经网络的单幅图像去雾算法.首先,依据大气散射物理模型进行理论推导,本文设计了一种能够直接学习和估计有雾图像和霾层图像之间的映射关系的网络模型.采用有雾图像作为输入,并输出有雾图像与无雾图像之间的残差图像,随后直接从有雾图像中去除此霾层图像,即可恢复出无雾图像.残差学习的引入,使得网络来直接估计初始霾层,利用相对大的学习率,减少计算量,加快收敛过程.再利用引导滤波进行细化,使得恢复出的无雾图像更接近真实场景.本文对不同雾浓度的有雾图片的去雾效果进行测试,并与当前主流深度学习去雾算法及其他经典算法进行对比.实验结果显示,本文设计的卷积神经网络模型在图像去雾的应用,不论在主观效果还是客观指标上,都有优势.     

基于改进暗通道算法的红外图像去雾研究

为了提高红外图像去雾的质量,采用改进暗通道算法。首先通过图像自身调节来获得较准确的大气光强,利用原图暗原色图以及亮原色图的调节因子得到更加接近图像真实值的大气光强;然后均方差判断去雾图像区域块的对比度,通过透射率伸缩系数和透射率增减系数来调节透射率;接着为避免去雾图像画质偏暗,通过灰度值大小对图像亮度进行校正;最后给出了算法流程。实验仿真显示本文算法没有色彩失真现象,边缘细节处理更清晰明亮,平均梯度值最少为6.0,信息熵最少为7.5,峰值信噪比最少为17.6dB,能够满足红外图像去雾对清晰度、信息量的要求。     

自适应高斯融合双通道的去雾算法

针对传统图像去雾算法存在的对比度下降和颜色偏移等问题,提出一种结合高斯融合的自适应双通道雾霾图像复原算法。首先,考虑到大气光应小于有雾图像最大值,且大于有雾图像最小值,根据亮度控制因子自适应控制的方式得到融合中通道,并获得中通道下的局部大气光;其次,提出双通道线性传输,即用最大值通道辅助完成线性传输,再用高斯函数加权融合的方法实现清晰图像最优通道估计,从而得到最优透射率;最后,结合复原模型恢复清晰图像。实验表明,所提方法有效解决了图像对比度下降与颜色偏移等问题,去雾效果良好、亮度适宜且颜色保真度更高。另外,该方法在定量指标上同样具有优越的表现。      

DCA-CycleGAN: Unsupervised single image dehazing using Dark Channel Attention optimized CycleGAN

Single image dehazing has great significance in computer vision. In this paper, we propose a novel unsupervised Dark Channel Attention optimized CycleGAN (DCA-CycleGAN) to deal with the challenging scene with uneven and dense haze concentration. Firstly, the DCA-CycleGAN adopts the dark channel as input and then generate attention through a DCA subnetwork to handle the nonhomogeneous haze. Secondly, in addition to the conventional global discriminator, we also leverage two local discriminators to enhance the dehazing performance on the local dense haze, and a new local adversarial loss calculated strategy is been proposed. Specifically, the dehazing generator consists of two subnetworks: an auto-encoder and a dark channel attention subnetwork. The auto-encoder consists of an encoder, a feature transformation module, and a decoder. The dark channel attention subnetwork has the same structure as the encoder and the feature transformation module to ensure the same receptive field, which utilizes the dark channel to generate attention map and fine-tune the auto-encoder. Experimental results against several state-of-the-art methods demonstrate that our method can generate better visual effects, and is effective.     

基于暗原色优化算法的去雾研究

针对基于传统的暗原色先验去雾算法中,由于某些场景下的雾天图像存在大面积明亮区域无法满足暗原色先验的假设,导致去雾效果不佳。文中就此问题提出了一种改进的去雾算法,基于McCartnet的理论建立大气散射模型,根据暗通道理论粗略估计透射率,之后引入容差参数并设置阈值,重新计算明亮区域的透射率,从而实现对明亮区域透射率的自校正。针对于复原图像色彩较暗的问题,采用改进的线性亮度调整方法来调节图像的亮度。实验结果显示,相较于原算法而言,改进算法可以有效的对大气光值进行估计,降低明亮区域的色彩失真,复原的图像可以保持足够的亮度,同时不丢失图像的细节,视觉效果显著提高。     

一种改进的透射率分布估计的夜间图像去雾算法

针对基于暗通道先验理论（dark channel prior, DCP）的去雾算法在处理夜间有雾图像时细节信息缺失、光源区域的纹理受损严重的问题,本文提出了一种改进的透射率分布估计的夜间图像去雾算法。通过引入暗态点光源模型、暗通道可信度权值因子和伪去雾图像,结合夜间图像成像模型,获取改进的透射率分布,对夜间降质图像进行去雾处理。实验结果表明,经本文算法处理后的图像在纹理细节上损失小、图像清晰度高,图像明暗对比度得到较好的拉伸,可以实现夜间有雾图像的有效去雾。     

分割映射的单幅彩色图像去雾方法

针对传统暗通道先验去雾方法在进行大气散射函 数估计时容易出现块状模糊效应的问题,提出了一种 基于分割映射的单幅彩色图像去雾方法。首先对前端采集图像进行近景与远景区域分 割,并基于分 割区域进行亮度信息的分段映射,通过分段计算获取大气散射函数的预测估计值;接着,采 用传统的导向 滤波方法对大气散射函数的估计值进行优化分析,进一步增强图像的边缘信息,改善在大面 积天空颜色情 况下图像边缘的块状模糊效应,提升含雾图像在突变区域的去雾效果。针对实际采集 的含雾图像进 行去雾效果分析和对比,分别基于图像的对比度改善量e、色彩自然度(CN I)、颜色丰富程度(CCI)以及计算耗时等4方面进行定量对比。分析结果表明, 本文方法很好地改善了图像的去雾效果,并进一步提升了运行的实时性。     

基于双通道及图像质量评价模型的去雾方法

针对传统暗通道先验去雾算法易产生明亮区域失 真、去雾图像整体偏暗等问题,提 出一种基于双通道及图像质量评价模型的去雾方法。首先,划分出图像的明亮区域与非明亮 区域;其次,利用双通道先验算法准确估计出大气光值;接下来,将暗通道先验的透射率作 为非明亮区域的透射率,在明亮区域单独构建透射率,将二者融合细化,得到带有参数的透 射率;最后,通过构造参数驱动图像质量评价模型,迭代选取最优的无雾图像。实验结果表 明,算法去雾效果良好,可以有效地抑制Halo效应,避免区域的失真,改善复原图像 的综合质量。