基于多先验约束和一致性正则的半监督图像去雾算法

针对合成雾霾图像训练的去雾模型在真实场景中去雾效果不佳、对高层视觉任务性能提升不明显等问题,该文提出一种基于多先验约束和一致性正则的半监督图像去雾算法。该方法采用编码器-解码器网络结构,同时在合成雾霾图像与真实雾霾图像上学习去雾映射,并利用多种统计先验去雾结果作为真实雾霾图像参考真值进行半监督学习,同时通过多张真实雾霾图像的随机混合进行一致性正则约束,以消除多种先验去雾结果差异以及噪声干扰,提高图像去雾结果的视觉质量。实验对比结果表明,所提算法可比现有方法获得更好的真实场景去雾结果,并且能够显著提升高层视觉任务性能。     

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.     

A modular architecture for high resolution image dehazing

Haze is an atmospheric phenomenon which diminishes visibility in outdoor images. Algorithms based on dark channel prior (DCP) and haze line prior are found to be effective for dehazing images. These two methods make use of the Laplacian matrix, which is computationally complex, memory intensive and slow, thus making it impossible to use them on high-resolution (large) images. Multiple strategies have been suggested in the literature to speed up dehazing process by avoiding the Laplacian matrix, but these methods compromise on the quality of dehazing. We propose an effective modular method which divides the input image into blocks and processes each block independently. This makes it possible to use our method for dehazing large images retaining Laplacian matting and thus ensuring the output image quality. This division results in the possibility of assuming local values of atmospheric light. We show that this approach results in better dehazing in the local regions. The effectiveness of the proposed modular architecture is tested also on a learning based method. The output of the modular method is compared with those of different state-of-the-art dehazing methods for multiple quality parameters. Toward this, we have created a dataset of hazy natural outdoor images of large size.     

基于迁移学习的三子网图像去雾方法

目前大部分图像去雾算法只在一种或几种均匀雾图数据集中有较好的表现,对于不同风格或非均匀雾图数据集去雾效果较差,同时算法在实际应用中会因模型泛化能力差导致模型场景受限。针对上述情况,该文提出一种基于迁移学习的卷积神经网络(CNN)用于解决去雾算法中非均匀雾图处理效果不佳和模型泛化能力差等问题。首先,该文使用ImageNet预训练的模型参数作为迁移学习模型的初始参数,以加速模型训练收敛速度。其次,主干网络模型由3个子网组成:残差特征子网络、局部特征提取子网络和整体特征提取子网络。3子网结合以保证模型可从整体和局部两个方面进行特征提取,在现实雾场景(浓雾、非均匀雾)中获得较好的去雾效果。该文在模型训练效率、去雾质量和雾图场景选择灵活性3个方面进行了研究和改进,为衡量模型性能,模型选择在去雾难度较大的非均匀雾图数据集NTIRE2020和NTIRE2021上进行定量与定性实验。实验结果证明3子网模型在图像主观和客观评价指标两个方面都取得了较好的效果。该文模型改善了算法泛化性能差和小数据集难以进行模型训练的问题,可将该文成果广泛应用于小规模数据集和多变场景图像的去雾工作中。     

A joint cumulative distribution function and gradient fusion based method for dehazing of long shot hazy images

Hazy or foggy weather conditions significantly degrade the visual quality of an image in an outdoor environment. It also changes the color and reduces the contrast of an image. This paper introduces a novel single image dehazing technique to restore a hazy image without considering the physical model of haze formation. In order to find haze-free image, the proposed method does not require the transmission map and its costly refinement process. Since haze effect is dependent on the depth, it severely degrades the visibility of the objects located at a far distance. The objects close to the camera are unaffected. In this paper, we propose a fusion-based haze removal method based on the joint cumulative distribution function (JCDF) that treats faraway haze and nearby haze separately. The output images after the JCDF module, fused in the gradient domain to produce a haze-free image. The proposed method not only significantly enhances visibility but also preserves texture details. The proposed method is experimented and evaluated on a large set of challenging hazy images (large scene depth, night time, dense fog, etc.). Both qualitative and quantitative measures show that the performance of the proposed method is better than the state-of-the-art dehazing techniques.     

Optimized contrast enhancement for real-time image and video dehazing

A fast and optimized dehazing algorithm for hazy images and videos is proposed in this work. Based on the observation that a hazy image exhibits low contrast in general, we restore the hazy image by enhancing its contrast. However, the overcompensation of the degraded contrast may truncate pixel values and cause information loss. Therefore, we formulate a cost function that consists of the contrast term and the information loss term. By minimizing the cost function, the proposed algorithm enhances the contrast and preserves the information optimally. Moreover, we extend the static image dehazing algorithm to real-time video dehazing. We reduce flickering artifacts in a dehazed video sequence by making transmission values temporally coherent. Experimental results show that the proposed algorithm effectively removes haze and is sufficiently fast for real-time dehazing applications.     

基于多尺度特征结合细节恢复的单幅图像去雾方法

为提高单幅图像去雾方法的准确性及其去雾结果的细节可见性,该文提出一种基于多尺度特征结合细节恢复的单幅图像去雾方法。首先,根据雾在图像中的分布特性及成像原理,设计多尺度特征提取模块及多尺度特征融合模块,从而有效提取有雾图像中与雾相关的多尺度特征并进行非线性加权融合。其次,构造基于所设计多尺度特征提取模块和多尺度特征融合模块的端到端去雾网络,并利用该网络获得初步去雾结果。再次,构造基于图像分块的细节恢复网络以提取细节信息。最后,将细节恢复网络提取出的细节信息与去雾网络得到的初步去雾结果融合得到最终清晰的去雾图像,实现对去雾后图像视觉效果的增强。实验结果表明,与已有代表性的图像去雾方法相比,所提方法能够对合成图像及真实图像中的雾进行有效去除,且去雾结果细节信息保留完整。     

一种基于反馈机制的闭环图像去雾算法

针对目前去雾算法易受大气环境随机性和复杂性影响而造成自适应性不强的问题,该文提出一种具有反馈机制的自适应闭环去雾算法。该算法首先通过基于人眼视觉的特征认知评价进行参数初始化;然后利用去雾强度评价结果对反馈校正局部对比度参数进行调节,从而对去除加性光照后的图像进行自适应局部对比度提升;最后借鉴去雾后图像的自然度设定迭代终止条件,决定是否输出去雾结果。实验表明该算法能够自适应提升不同退化类型、不同退化程度下的雾天图像对比度,且去雾结果的信息熵和清晰度质量评价指标优于已有算法。     

From synthetic to natural — single natural image dehazing deep networks using synthetic dataset domain randomization

Image dehazing methods aim to solve the problem of poor visibility in images due to haze. Techniques proposed for image dehazing in literature focus on image priors, haze lines or data driven statistical models. Variations of the classical methods relying on prior model or haze line model use no-reference image quality metrics to prove their dehazing performance. Recently developed deep learning models rely on huge amounts of hazy, haze-free pairs for training, and uses PSNR and SSIM like image reconstruction metrics to show their performance. These methods perform poorly on no-reference image quality assessments and also dehazes poorly at the depths of the image. These methods though can be optimized for memory usage and are faster. This work presents a deep learning model (Feature Fusion Attention Network) trained on a domain randomized synthetic dataset generated in simulation. The proposed model achieves the highest scores on blind image assessments through the gradient rationing technique for a deep learning-based approach by a significant margin. The images were evaluated on full-reference metrics as well and obtained favorable results. This approach also yields one of the highest edge sharpness obtained after dehazing. The training procedure adopted to obtain significant gains on real-world dehazing, without using any real-world data is also detailed in this paper.     

基于光照估计的夜间图像去雾

相对白天雾天图像,夜晚雾天图像具有整体亮度低、光照不均匀、偏色等特点,因此去雾难度大。本文从夜间雾天成像规律出发,提出了基于光照估计的夜间图像去雾算法。针对光照不均匀问题,通过估计光照图来去除不均匀光照的影响;针对目前白天去雾算法假设不适用于夜晚图像问题,提出基于信息熵的传输图粗估计的方法;针对颜色失真问题,通过统计光源区域的颜色属性来进行颜色校正。实验结果表明,本文算法能够有效的去除不均匀光照影响,提高图像对比度,改善图像视觉效果。     

Real-world image dehazing with improved joint enhancement and exposure fusion

In this work, a single image dehazing method that improves the haze removal capacity of the Joint Contrast Enhancement and Exposure Fusion (CEEF) method with Smoothing-Sharpening Image Filter (SSIF) is presented. In this method, the hazy image is first sharpened with SSIF to obtain a sharper image. In this way, the difference between haze and objects is amplified. Then, the AHE procedure in CEEF is replaced by CLAHE to obtain an enhanced CEEF. The enhanced CEEF is applied to the filtering result to obtain the final dehazed image. Observations demonstrate that the proposed method obtains enhanced results while reducing the amount of haze. The visual and quantitative comparisons between the proposed method and state-of-the-art dehazing methods show that the proposed method has better dehazing performance and has a 50% improvement in terms of the FADE metric compared to the closest result.     

暗原色先验自适应图像去雾方法

针对传统暗原色先验去雾算法存在的亮区域色彩失真、去雾参 数人工设定等问题,提出了一种基于暗原色先验改进的自适应图像去雾方法。首先,提出快 速OSTU法对雾霾图像亮暗区域进行自适应分割,并分区域获取亮暗区域的暗原色值;其次, 根据亮区域分布情况,对不同区域大气光强进行自适应估计;接着,通过分析雾霾图像直方 图特征,提出采用灰度集中度法自适应计算去雾系数;然后,运用色阶自适应调整方法进行 输出图像的色彩调整;最后,通过开展对比实验,验证了本文算法的优越性。主客观 评价结果表明:本文方法无需人为设定去雾参数,具有较好的 鲁棒性,可适用于多种浓度、 各种场景雾霾图像的去雾处理,获取的图像清晰、色彩自然,对比度高。     

图像去雾过程中的噪声抑制方法

大气中微小颗粒（如雾、霾等）的散射作用会使户外场景拍摄的图像发生退化,造成图像质量下降。图像去雾可以提升图像对比度,增加场景能见度,校正颜色失真,改善视觉效果。但是图像去雾经常会出现明显的噪声放大现象,尤其是无穷远处的天空区域最为严重。针对这一问题,提出了一种去雾过程中的噪声抑制方法。以传输率图像为指导,采用滤波半径变化的双边滤波对雾天图像进行模糊。再计算新的传输率图像,代入雾天成像模型,得到去噪后复原图像。结合噪声评价方法,实验结果验证了该方法的噪声抑制效果。     

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。     

Single image dehazing using a new color channel

Images with hazy scene suffer from low-contrast, which reduces the visible quality of the scene, thus making object detection a more challenging task. Low-contrast can result from foggy weather conditions during image acquisition. Dehazing is a process of removal of haze from the photography of a hazy scene. Single-image dehazing based on dark channel priors are well-known techniques in this field. However, the performance of such techniques is limited to priors or constraints. Moreover, this type of method fails when images have sky-region. So, a method is proposed, which can restore the visibility of hazy images. First, a hazy image is divided into blocks of size 32 × 32, then the score of each block is calculated to select a block having the highest score. Atmospheric light is calculated from the selected block. A new color channel is considered to remove atmospheric scattering, obtained channel value and atmospheric light are then used to calculate the transmission map in the second step. Third, radiance is computed using a transmission map and atmospheric light. The illumination scaling factor is adopted to enhance the quality of a dehazed image in the final step. Experiments are performed on six datasets namely, I-HAZE, O-HAZE, BSDS500, FRIDA, RESIDE dataset and natural images from Google. The proposed method is compared against 11 state-of-the-art methods. The performance is analyzed using fourteen quantitative evaluation metrics. All the results demonstrate that the proposed method outperforms 11 state-of-the-art methods in most of the cases.     

基于快速引导滤波改进的暗原色先验去雾算法

针对目前单幅雾霾降质图像存在大面积天空域,导致暗原色失效复原图像失真以及去雾时间复杂度高的问题.提出一种基于暗原色先验和快速引导滤波的去雾方法,针对存在高亮天空域图像多尺度滤波采用自适应阈值分割得到天空域,在天空域求取精确大气光值,再将天空域和非天空域透射率有效归一化,最后采用暗通道图作为引导图快速引导滤波精细化透射率,最大限度保留边缘细节的同时有效降低时间复杂度.实验结果表明,该方法可以有效处理天空域,保持色彩和细节信息,在算法实时性上有明显优势.     

动态大气散射系数的颜色衰减先验图像去雾

针对颜色衰减先验图像去雾算法存在对较浓的有雾图像去雾效果不佳的问题,提出基于动态大气散射系数的颜色衰减先验图像去雾算法.用动态大气散射系数取代颜色衰减先验去雾算法中恒定大气散射系数的假设,定义大气散射系数为关于图像景深的指数函数.利用Middlebury stereo datasets中无雾图像和相应的景深图像得到合成有雾图像.采用均方误差(MSE)和结构相似度(SSIM)的综合评价参数MSE-SSIM确定上述指数函数的两个参数的最佳取值.实验结果表明与颜色衰减先验算法、He、Meng算法相比,该算法的去雾图像清晰颜色自然,有效地提高了去雾效果.     

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.     

基于双注意力机制的雾天图像清晰化算法研究

针对传统去雾算法容易依赖先验知识以及恢复出来的清晰图像会产生颜色失真等问题,本文提出一种基于双注意力机制的雾天图像清晰化算法。首先将雾图输入编码器,经过下采样后得到特征图像;特征提取模块将多个特征提取基本块联结在一起,每个基本块由局部残差学习和特征注意模块组成,提高图像质量以及图像特征信息的利用率,增加网络训练的稳定性;然后通过通道注意力与多尺度空间注意力并行的结构处理特征图像,使得网络更加关注细节特征,提取更多关键信息,同时提高网络效率;最后将融合后的特征图像输入解码器中,经过多级映射,得到与输入大小匹配的雾密度图。实验结果表明,不论是对合成雾天图像或者真实雾天图像,本文算法能够高效地进行去雾处理,得到更自然的清晰图像。     

基于透射率权值因子的雾天图像融合增强算法

雾天图像增强具有重要现实意义。由于现有的图像去雾算法在提升图像全局对比度的能力上存在不足,为此将暗通道先验去雾算法与直方图均衡化算法的各自优势进行整合,该文提出一种雾天图像增强新算法。首先,分别采用基于导向滤波的暗通道先验去雾算法和基于HSV色彩空间的直方图均衡化算法处理雾天图像;然后,基于修正的透射率图构造权值因子,将上述两种处理结果加权融合,得到输出图像。仿真实验结果表明,该算法比现有去雾算法具有更高的标准差、平均梯度与信息熵,具有更好的全局与局部对比度增强效果。算法运行时间主要依赖于图像去雾环节,处理一般尺寸图像能够满足实时要求。