在合成数据集接受培训的基于深度学习的源脱掩护方法已经取得了显着的性能,但由于域移动而引起的真实朦胧图像的性能急剧下降。尽管已经提出了某些域的适应(DA)脱掩护方法,但它们不可避免地需要访问源数据集,以减少源合成和目标真实域之间的差距。为了解决这些问题,我们提出了一种新颖的无源无监督的域适应性(SFUDA)图像去悬式范式,其中只有训练有素的源模型和未标记的目标真实的朦胧数据集。具体而言,我们设计了域表示标准化(DRN)模块,以使真实朦胧域特征的表示与合成域的特征相匹配以弥合间隙。借助我们的插件DRN模块,未标记的真实朦胧图像可以调整现有训练有素的源网络。此外,还应用了无监督的损失来指导DRN模块的学习,该模块包括频率损失和物理先验损失。频率损失提供了结构和样式的约束,而先前的损失探讨了无雾图像的固有统计属性。现有的源脱去模型配备了我们的DRN模块和无监督的损失,能够脱光未标记的真实朦胧图像。在多个基层上进行的广泛实验证明了我们方法在视觉和定量上的有效性和优越性。
translated by 谷歌翻译
With the development of convolutional neural networks, hundreds of deep learning based dehazing methods have been proposed. In this paper, we provide a comprehensive survey on supervised, semi-supervised, and unsupervised single image dehazing. We first discuss the physical model, datasets, network modules, loss functions, and evaluation metrics that are commonly used. Then, the main contributions of various dehazing algorithms are categorized and summarized. Further, quantitative and qualitative experiments of various baseline methods are carried out. Finally, the unsolved issues and challenges that can inspire the future research are pointed out. A collection of useful dehazing materials is available at \url{https://github.com/Xiaofeng-life/AwesomeDehazing}.
translated by 谷歌翻译
我们提出了一种增强的多尺度网络,被称为GriddehazeNet +,用于单图像脱水。所提出的去吸收方法不依赖于大气散射模型(ASM),并提供为什么不一定执行该模型提供的尺寸减少的原因。 Griddehazenet +由三个模块组成:预处理,骨干和后处理。与手工选定的预处理方法产生的那些导出的输入相比,可训练的预处理模块可以生成具有更好分集和更相关的功能的学习输入。骨干模块实现了两种主要增强功能的多尺度估计:1)一种新颖的网格结构,有效地通过不同尺度的密集连接来减轻瓶颈问题; 2)一种空间通道注意力块,可以通过巩固脱水相关特征来促进自适应融合。后处理模块有助于减少最终输出中的伪像。由于域移位,在合成数据上培训的模型可能在真实数据上概括。为了解决这个问题,我们塑造了合成数据的分布以匹配真实数据的分布,并使用所产生的翻译数据来到Finetune我们的网络。我们还提出了一种新的任务内部知识转移机制,可以记住和利用综合域知识,以协助学习过程对翻译数据。实验结果表明,所提出的方法优于几种合成脱色数据集的最先进,并在FineTuning之后实现了现实世界朦胧图像的优越性。
translated by 谷歌翻译
Deep learning-based methods have achieved significant performance for image defogging. However, existing methods are mainly developed for land scenes and perform poorly when dealing with overwater foggy images, since overwater scenes typically contain large expanses of sky and water. In this work, we propose a Prior map Guided CycleGAN (PG-CycleGAN) for defogging of images with overwater scenes. To promote the recovery of the objects on water in the image, two loss functions are exploited for the network where a prior map is designed to invert the dark channel and the min-max normalization is used to suppress the sky and emphasize objects. However, due to the unpaired training set, the network may learn an under-constrained domain mapping from foggy to fog-free image, leading to artifacts and loss of details. Thus, we propose an intuitive Upscaling Inception Module (UIM) and a Long-range Residual Coarse-to-fine framework (LRC) to mitigate this issue. Extensive experiments on qualitative and quantitative comparisons demonstrate that the proposed method outperforms the state-of-the-art supervised, semi-supervised, and unsupervised defogging approaches.
translated by 谷歌翻译
Recovery of true color from underwater images is an ill-posed problem. This is because the wide-band attenuation coefficients for the RGB color channels depend on object range, reflectance, etc. which are difficult to model. Also, there is backscattering due to suspended particles in water. Thus, most existing deep-learning based color restoration methods, which are trained on synthetic underwater datasets, do not perform well on real underwater data. This can be attributed to the fact that synthetic data cannot accurately represent real conditions. To address this issue, we use an image to image translation network to bridge the gap between the synthetic and real domains by translating images from synthetic underwater domain to real underwater domain. Using this multimodal domain adaptation technique, we create a dataset that can capture a diverse array of underwater conditions. We then train a simple but effective CNN based network on our domain adapted dataset to perform color restoration. Code and pre-trained models can be accessed at https://github.com/nehamjain10/TRUDGCR
translated by 谷歌翻译
Image restoration under hazy weather condition, which is called single image dehazing, has been of significant interest for various computer vision applications. In recent years, deep learning-based methods have achieved success. However, existing image dehazing methods typically neglect the hierarchy of features in the neural network and fail to exploit their relationships fully. To this end, we propose an effective image dehazing method named Hierarchical Contrastive Dehazing (HCD), which is based on feature fusion and contrastive learning strategies. HCD consists of a hierarchical dehazing network (HDN) and a novel hierarchical contrastive loss (HCL). Specifically, the core design in the HDN is a Hierarchical Interaction Module, which utilizes multi-scale activation to revise the feature responses hierarchically. To cooperate with the training of HDN, we propose HCL which performs contrastive learning on hierarchically paired exemplars, facilitating haze removal. Extensive experiments on public datasets, RESIDE, HazeRD, and DENSE-HAZE, demonstrate that HCD quantitatively outperforms the state-of-the-art methods in terms of PSNR, SSIM and achieves better visual quality.
translated by 谷歌翻译
基于深度学习的低光图像增强方法通常需要巨大的配对训练数据,这对于在现实世界的场景中捕获是不切实际的。最近,已经探索了无监督的方法来消除对成对训练数据的依赖。然而,由于没有前衣,它们在不同的现实情景中表现得不稳定。为了解决这个问题,我们提出了一种基于先前(HEP)的有效预期直方图均衡的无监督的低光图像增强方法。我们的作品受到了有趣的观察,即直方图均衡增强图像的特征图和地面真理是相似的。具体而言,我们制定了HEP,提供了丰富的纹理和亮度信息。嵌入一​​个亮度模块(LUM),它有助于将低光图像分解为照明和反射率图,并且反射率图可以被视为恢复的图像。然而,基于Retinex理论的推导揭示了反射率图被噪声污染。我们介绍了一个噪声解剖学模块(NDM),以解除反射率图中的噪声和内容,具有不配对清洁图像的可靠帮助。通过直方图均衡的先前和噪声解剖,我们的方法可以恢复更精细的细节,更有能力抑制现实世界低光场景中的噪声。广泛的实验表明,我们的方法对最先进的无监督的低光增强算法有利地表现出甚至与最先进的监督算法匹配。
translated by 谷歌翻译
基于对抗性学习的图像抑制方法,由于其出色的性能,已经在计算机视觉中进行了广泛的研究。但是,大多数现有方法对实际情况的质量功能有限,因为它们在相同场景的透明和合成的雾化图像上进行了培训。此外,它们在保留鲜艳的色彩和丰富的文本细节方面存在局限性。为了解决这些问题,我们开发了一个新颖的生成对抗网络,称为整体注意力融合对抗网络(HAAN),用于单个图像。 Haan由Fog2FogFogre块和FogFree2Fog块组成。在每个块中,有三个基于学习的模块,即雾除雾,颜色纹理恢复和雾合成,它们相互限制以生成高质量的图像。 Haan旨在通过学习雾图图像之间的整体通道空间特征相关性及其几个派生图像之间的整体通道空间特征相关性来利用纹理和结构信息的自相似性。此外,在雾合成模块中,我们利用大气散射模型来指导它,以通过新颖的天空分割网络专注于大气光优化来提高生成质量。关于合成和现实世界数据集的广泛实验表明,就定量准确性和主观的视觉质量而言,Haan的表现优于最先进的脱落方法。
translated by 谷歌翻译
水下图像由于光吸收,折射率和散射而受到颜色铸造,低对比度和朦胧效果,这些效果降低了高级应用,例如,对象检测和对象跟踪。最新的基于学习的方法证明了水下图像增强的惊人性能,但是,这些作品中的大多数使用合成对数据进行监督学习,并忽略了对现实世界数据的域间隙。为了解决这个问题,我们提出了一个通过内容和样式分离来增强水下图像的域适应框架,不同于水下图像增强的域适应性作品,该框架的目标是最大程度地减少合成和现实世界的潜在差异,我们的目标将编码功能分离为内容和样式潜在的样式,并将潜在的样式与不同的域,即合成,现实世界的水下和清洁域以及潜在空间中的过程域的适应和图像增强。通过潜在的操纵,我们的模型提供了一个用户交互接口,以调整不同的增强级别以进行连续更改。对各种公共水下基准测试的实验表明,所提出的框架能够对水下图像增强的域进行适应性,并在数量和质量方面胜过各种最先进的水下图像增强算法。该型号和源代码将在https://github.com/fordevoted/uiess上找到
translated by 谷歌翻译
One of the main challenges in deep learning-based underwater image enhancement is the limited availability of high-quality training data. Underwater images are difficult to capture and are often of poor quality due to the distortion and loss of colour and contrast in water. This makes it difficult to train supervised deep learning models on large and diverse datasets, which can limit the model's performance. In this paper, we explore an alternative approach to supervised underwater image enhancement. Specifically, we propose a novel unsupervised underwater image enhancement framework that employs a conditional variational autoencoder (cVAE) to train a deep learning model with probabilistic adaptive instance normalization (PAdaIN) and statistically guided multi-colour space stretch that produces realistic underwater images. The resulting framework is composed of a U-Net as a feature extractor and a PAdaIN to encode the uncertainty, which we call UDnet. To improve the visual quality of the images generated by UDnet, we use a statistically guided multi-colour space stretch module that ensures visual consistency with the input image and provides an alternative to training using a ground truth image. The proposed model does not need manual human annotation and can learn with a limited amount of data and achieves state-of-the-art results on underwater images. We evaluated our proposed framework on eight publicly-available datasets. The results show that our proposed framework yields competitive performance compared to other state-of-the-art approaches in quantitative as well as qualitative metrics. Code available at https://github.com/alzayats/UDnet .
translated by 谷歌翻译
在弱照明条件下捕获的图像可能会严重降低图像质量。求解一系列低光图像的降解可以有效地提高图像的视觉质量和高级视觉任务的性能。在本研究中,提出了一种新的基于RETINEX的实际网络(R2RNET),用于低光图像增强,其包括三个子网:DECOM-NET,DENOISE-NET和RELIGHT-NET。这三个子网分别用于分解,去噪,对比增强和细节保存。我们的R2RNET不仅使用图像的空间信息来提高对比度,还使用频率信息来保留细节。因此,我们的模型对所有退化的图像进行了更强大的结果。与在合成图像上培训的最先前的方法不同,我们收集了第一个大型现实世界配对的低/普通灯图像数据集(LSRW数据集),以满足培训要求,使我们的模型具有更好的现实世界中的泛化性能场景。对公共数据集的广泛实验表明,我们的方法在定量和视觉上以现有的最先进方法优于现有的现有方法。此外,我们的结果表明,通过使用我们在低光条件下的方法获得的增强的结果,可以有效地改善高级视觉任务(即面部检测)的性能。我们的代码和LSRW数据集可用于:https://github.com/abcdef2000/r2rnet。
translated by 谷歌翻译
由于难以收集配对的现实世界训练数据,因此图像deraining目前由监督学习主导,并通过Photoshop渲染生成的合成数据。但是,由于合成数据和现实世界数据之间的差距,通常限制了对真实下雨场景的概括。在本文中,我们首先从统计学上探讨了为什么监督模型不能很好地推广到真实的雨天,并找到合成和真实雨水数据的实质差异。受我们的研究的启发,我们建议通过从其他连接的任务中学习有利的代表来消除雨水。在连接的任务中,可以轻松获得真实数据的标签。因此,我们的核心思想是通过任务传输从真实数据中学习表示形式,以改善概括。因此,我们将学习策略称为\ textit {任务传输学习}。如果有多个连接的任务,我们建议通过知识蒸馏降低模型大小。连接任务的预处理模型被视为教师,他们的所有知识都被蒸馏到学生网络,以便我们减少模型规模,同时保留所有连接的任务中有效的先前表示。最后,学生网络对少数配对的合成雨数据进行了微调,以指导预定的先前表示以去除雨水。广泛的实验表明,提出的任务转移学习策略令人惊讶地成功,并与最先进的监督学习方法相比,并显然超过了其他半监督者在合成数据上的方法。特别是,它显示出对现实世界的概括性的概括。
translated by 谷歌翻译
Images with haze of different varieties often pose a significant challenge to dehazing. Therefore, guidance by estimates of haze parameters related to the variety would be beneficial and their progressive update jointly with haze reduction will allow effective dehazing. To this end, we propose a multi-network dehazing framework containing novel interdependent dehazing and haze parameter updater networks that operate in a progressive manner. The haze parameters, transmission map and atmospheric light, are first estimated using specific convolutional networks allowing color-cast handling. The estimated parameters are then used to guide our dehazing module, where the estimates are progressively updated by novel convolutional networks. The updating takes place jointly with progressive dehazing by a convolutional network that invokes inter-step dependencies. The joint progressive updating and dehazing gradually modify the haze parameter estimates toward achieving effective dehazing. Through different studies, our dehazing framework is shown to be more effective than image-to-image mapping or predefined haze formation model based dehazing. Our dehazing framework is qualitatively and quantitatively found to outperform the state-of-the-art on synthetic and real-world hazy images of several datasets with varied haze conditions.
translated by 谷歌翻译
我们从一组未配对的清晰和朦胧的图像中提供了实用的基于学习的图像飞行网络。本文提供了一种新的观点,可以将图像除去作为两类分离的因子分离任务,即清晰图像重建的任务相关因素以及与雾霾相关的分布的任务含量。为了在深度特征空间中实现这两类因素的分离,将对比度学习引入了一个自行车框架中,以通过指导与潜在因素相关的生成的图像来学习分离的表示形式。通过这种表述,提出的对比度拆除的脱掩护方法(CDD-GAN)采用负面发电机与编码器网络合作以交替进行更新,以产生挑战性负面对手的队列。然后,这些负面的对手是端到端训练的,以及骨干代表网络,以通过最大化对抗性对比损失来增强歧视性信息并促进因素分离性能。在培训期间,我们进一步表明,硬性负面例子可以抑制任务 - 无关紧要的因素和未配对的清晰景象可以增强与任务相关的因素,以便更好地促进雾霾去除并帮助图像恢复。对合成和现实世界数据集的广泛实验表明,我们的方法对现有的未配对飞行基线的表现良好。
translated by 谷歌翻译
水下图像不可避免地会受到颜色失真和对比度减少的影响。基于统计的方法,例如白平衡和直方图拉伸,试图调整颜色通道的不平衡和狭窄的强度分布,因此性能有限。最近,基于深度学习的方法取得了令人鼓舞的结果。但是,所涉及的架构复杂化和高计算成本可能会阻碍其在实用的约束平台中的部署。受上述作品的启发,我们提出了一个统计学的轻量级水下图像增强网络(USLN)。具体而言,我们首先开发一个双统计的白平衡模块,该模块可以学会使用平均图像和最大图像来补偿每个特定像素的颜色失真。然后是一个多色空间拉伸模块,以适应RGB,HSI和实验室颜色空间中的直方图分布。广泛的实验表明,在统计数据的指导下,USLN大大降低了所需的网络容量(超过98%)并实现最先进的性能。代码和相关资源可在https://github.com/deepxzy/usln上获得。
translated by 谷歌翻译
在低灯条件下捕获的图像遭受低可视性和各种成像伪影,例如真实噪音。现有的监督启示算法需要大量的像素对齐的训练图像对,这很难在实践中准备。虽然弱监督或无人监督的方法可以缓解这些挑战,但不使用配对的训练图像,由于缺乏相应的监督,一些现实世界的文物不可避免地被错误地放大。在本文中,而不是使用完美的对齐图像进行培训,我们创造性地使用未对准的现实世界图像作为指导,这很容易收集。具体地,我们提出了一个交叉图像解剖线程(CIDN),以分别提取来自低/常光图像的交叉图像亮度和图像特定内容特征。基于此,CIDN可以同时校正特征域中的亮度和抑制图像伪像,其在很大程度上将鲁棒性增加到像素偏移。此外,我们收集了一个新的低光图像增强数据集,包括具有现实世界腐败的未对准培训图像。实验结果表明,我们的模型在新建议的数据集和其他流行的低光数据集中实现了最先进的表演。
translated by 谷歌翻译
低光图像增强旨在提高图像的可见性,同时保持其视觉自然。与现有方法不同,倾向于直接通过忽略保真度和自然恢复来完成致密任务,我们调查内在的退化和赖光图像,同时改进细节和颜色两步。灵感来自彩色图像配方(漫反射颜色加环境照明颜色),我们首先估计低光输入的劣化,以模拟环境照明颜色的失真,然后优化内容以恢复漫反射照明颜色的损失。为此,我们提出了一种新的劣化到精炼生成网络(DRGN)。其独特的特点可以总结为1)一种新型的两步生成网络,用于降解学习和内容细化。它不仅优于一步法,还能够合成足够的配对样本来利用模型培训; 2)多分辨率融合网络以多规模的协作方式表示目标信息(劣化或内容),这更有效地解决复杂的解密问题。关于增强任务和联合检测任务的广泛实验已经验证了我们提出的方法的有效性和效率,分别超过了SOTA \ Texit {0.70dB平均值和地图}。代码可用于\ URL {https://github.com/kuijiang0802/drgn}。
translated by 谷歌翻译
As a common weather, rain streaks adversely degrade the image quality. Hence, removing rains from an image has become an important issue in the field. To handle such an ill-posed single image deraining task, in this paper, we specifically build a novel deep architecture, called rain convolutional dictionary network (RCDNet), which embeds the intrinsic priors of rain streaks and has clear interpretability. In specific, we first establish a RCD model for representing rain streaks and utilize the proximal gradient descent technique to design an iterative algorithm only containing simple operators for solving the model. By unfolding it, we then build the RCDNet in which every network module has clear physical meanings and corresponds to each operation involved in the algorithm. This good interpretability greatly facilitates an easy visualization and analysis on what happens inside the network and why it works well in inference process. Moreover, taking into account the domain gap issue in real scenarios, we further design a novel dynamic RCDNet, where the rain kernels can be dynamically inferred corresponding to input rainy images and then help shrink the space for rain layer estimation with few rain maps so as to ensure a fine generalization performance in the inconsistent scenarios of rain types between training and testing data. By end-to-end training such an interpretable network, all involved rain kernels and proximal operators can be automatically extracted, faithfully characterizing the features of both rain and clean background layers, and thus naturally lead to better deraining performance. Comprehensive experiments substantiate the superiority of our method, especially on its well generality to diverse testing scenarios and good interpretability for all its modules. Code is available in \emph{\url{https://github.com/hongwang01/DRCDNet}}.
translated by 谷歌翻译
最近3D点云学习一直是计算机视觉和自主驾驶中的热门话题。由于事实上,难以手动注释一个定性的大型3D点云数据集,无监督的域适应(UDA)在3D点云学习中流行,旨在将学习知识从标记的源域转移到未标记的目标领域。然而,具有简单学习模型引起的域转移引起的泛化和重建误差是不可避免的,这基本上阻碍了模型的学习良好表示的能力。为了解决这些问题,我们提出了一个结束到底自组合网络(SEN),用于3D云域适应任务。一般来说,我们的森林度假前的含义教师和半监督学习的优势,并引入了软的分类损失和一致性损失,旨在实现一致的泛化和准确的重建。在森中,学生网络以具有监督的学习和自我监督学习的协作方式,教师网络进行时间一致性,以学习有用的表示,并确保点云重建的质量。在几个3D点云UDA基准上的广泛实验表明,我们的SEN在分类和分段任务中表现出最先进的方法。此外,进一步的分析表明,我们的森也实现了更好的重建结果。
translated by 谷歌翻译
基于无监督的域适应性(UDA),由于目标情景的表现有希望的表现,面部抗散热器(FAS)方法引起了人们的注意。大多数现有的UDA FAS方法通常通过对齐语义高级功能的分布来拟合受过训练的模型。但是,对未标记的目标域的监督不足,低水平特征对齐降低了现有方法的性能。为了解决这些问题,我们提出了UDA FAS的新颖观点,该视角将目标数据直接适合于模型,即,通过图像翻译将目标数据风格化为源域样式,并进一步将风格化的数据提供给训练有素的数据分类的源模型。提出的生成域适应(GDA)框架结合了两个精心设计的一致性约束:1)域间神经统计量的一致性指导发生器缩小域间间隙。 2)双层语义一致性确保了风格化图像的语义质量。此外,我们提出了域内频谱混合物,以进一步扩大目标数据分布,以确保概括并减少域内间隙。广泛的实验和可视化证明了我们方法对最新方法的有效性。
translated by 谷歌翻译