Discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance. In this paper, we take one step forward by investigating the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress in very deep architecture, learning algorithm, and regularization method into image denoising. Specifically, residual learning and batch normalization are utilized to speed up the training process as well as boost the denoising performance. Different from the existing discriminative denoising models which usually train a specific model for additive white Gaussian noise (AWGN) at a certain noise level, our DnCNN model is able to handle Gaussian denoising with unknown noise level (i.e., blind Gaussian denoising). With the residual learning strategy, DnCNN implicitly removes the latent clean image in the hidden layers. This property motivates us to train a single DnCNN model to tackle with several general image denoising tasks such as Gaussian denoising, single image super-resolution and JPEG image deblocking. Our extensive experiments demonstrate that our DnCNN model can not only exhibit high effectiveness in several general image denoising tasks, but also be efficiently implemented by benefiting from GPU computing.
translated by 谷歌翻译
Model-based optimization methods and discriminative learning methods have been the two dominant strategies for solving various inverse problems in low-level vision. Typically, those two kinds of methods have their respective merits and drawbacks, e.g., model-based optimization methods are flexible for handling different inverse problems but are usually time-consuming with sophisticated priors for the purpose of good performance; in the meanwhile, discriminative learning methods have fast testing speed but their application range is greatly restricted by the specialized task. Recent works have revealed that, with the aid of variable splitting techniques, denoiser prior can be plugged in as a modular part of model-based optimization methods to solve other inverse problems (e.g., deblurring). Such an integration induces considerable advantage when the denoiser is obtained via discriminative learning. However, the study of integration with fast discriminative denoiser prior is still lacking. To this end, this paper aims to train a set of fast and effective CNN (convolutional neural network) denoisers and integrate them into model-based optimization method to solve other inverse problems. Experimental results demonstrate that the learned set of denoisers not only achieve promising Gaussian denoising results but also can be used as prior to deliver good performance for various low-level vision applications.
translated by 谷歌翻译
Recent years have witnessed the unprecedented success of deep convolutional neural networks (CNNs) in single image super-resolution (SISR). However, existing CNN-based SISR methods mostly assume that a low-resolution (LR) image is bicubicly downsampled from a high-resolution (HR) image, thus inevitably giving rise to poor performance when the true degradation does not follow this assumption. Moreover, they lack scalability in learning a single model to nonblindly deal with multiple degradations. To address these issues, we propose a general framework with dimensionality stretching strategy that enables a single convolutional super-resolution network to take two key factors of the SISR degradation process, i.e., blur kernel and noise level, as input. Consequently, the super-resolver can handle multiple and even spatially variant degradations, which significantly improves the practicability. Extensive experimental results on synthetic and real LR images show that the proposed convolutional super-resolution network not only can produce favorable results on multiple degradations but also is computationally efficient, providing a highly effective and scalable solution to practical SISR applications.
translated by 谷歌翻译
盲图修复(IR)是计算机视觉中常见但充满挑战的问题。基于经典模型的方法和最新的深度学习(DL)方法代表了有关此问题的两种不同方法,每种方法都有自己的优点和缺点。在本文中,我们提出了一种新颖的盲图恢复方法,旨在整合它们的两种优势。具体而言,我们为盲IR构建了一个普通的贝叶斯生成模型,该模型明确描绘了降解过程。在此提出的模型中,PICEL的非I.I.D。高斯分布用于适合图像噪声。它的灵活性比简单的I.I.D。在大多数常规方法中采用的高斯或拉普拉斯分布,以处理图像降解中包含的更复杂的噪声类型。为了解决该模型,我们设计了一个变异推理算法,其中所有预期的后验分布都被参数化为深神经网络,以提高其模型能力。值得注意的是,这种推论算法诱导统一的框架共同处理退化估计和图像恢复的任务。此外,利用了前一种任务中估计的降解信息来指导后一种红外过程。对两项典型的盲型IR任务进行实验,即图像降解和超分辨率,表明所提出的方法比当前最新的方法实现了卓越的性能。
translated by 谷歌翻译
经典图像去噪方法利用非本地自相似原理来有效地从嘈杂的图像中恢复图像内容。目前的最先进的方法使用深卷积神经网络(CNNS),以有效地学习从嘈杂到清洁图像的映射。深度去噪CNNS表现出高学习能力,并集成了由于大量隐藏层所产生的大型接收领域而整合非本地信息。然而,深网络也是计算复杂的并且需要大数据进行培训。为了解决这些问题,本研究旨在通过一种新的神经元模型赋予自组织的操作神经网络(自我onns)的重点,该模型可以通过紧凑且浅的模型实现类似或更好的去噪性能。最近,已经引入了超神经元的概念,其通过利用未局限性的内核位置来增强生成神经元的非线性变换,以获得增强的接受场大小。这是赋予深度网络配置需求的关键成就。由于已知非本地信息的整合受益于去噪,在这项工作中,我们研究了超神经元对合成和现实世界图像去噪的使用。我们还讨论了在GPU上实施超神经元模型的实际问题,并提出了非本地化操作的异质性与计算复杂性之间的权衡。我们的结果表明,具有相同的宽度和深度,具有超级神经元的自动onn,具有对具有生成和卷积神经元的网络的去噪性能,为脱结任务提供了显着的促进。此外,结果表明,具有超神经元的自串,可以分别为合成和真实世界的众所周知的众所周知的深层CNN去噪者达到竞争和优越的合成表演。
translated by 谷歌翻译
本文提出了图像恢复的新变异推理框架和一个卷积神经网络(CNN)结构,该结构可以解决所提出的框架所描述的恢复问题。较早的基于CNN的图像恢复方法主要集中在网络体系结构设计或培训策略上,具有非盲方案,其中已知或假定降解模型。为了更接近现实世界的应用程序,CNN还接受了整个数据集的盲目培训,包括各种降解。然而,给定有多样化的图像的高质量图像的条件分布太复杂了,无法通过单个CNN学习。因此,也有一些方法可以提供其他先验信息来培训CNN。与以前的方法不同,我们更多地专注于基于贝叶斯观点以及如何重新重新重构目标的恢复目标。具体而言,我们的方法放松了原始的后推理问题,以更好地管理子问题,因此表现得像分裂和互动方案。结果,与以前的框架相比,提出的框架提高了几个恢复问题的性能。具体而言,我们的方法在高斯denoising,现实世界中的降噪,盲图超级分辨率和JPEG压缩伪像减少方面提供了最先进的性能。
translated by 谷歌翻译
We present a highly accurate single-image superresolution (SR) method. Our method uses a very deep convolutional network inspired by VGG-net used for ImageNet classification [19]. We find increasing our network depth shows a significant improvement in accuracy. Our final model uses 20 weight layers. By cascading small filters many times in a deep network structure, contextual information over large image regions is exploited in an efficient way. With very deep networks, however, convergence speed becomes a critical issue during training. We propose a simple yet effective training procedure. We learn residuals only and use extremely high learning rates (10 4 times higher than SRCNN [6]) enabled by adjustable gradient clipping. Our proposed method performs better than existing methods in accuracy and visual improvements in our results are easily noticeable.
translated by 谷歌翻译
Recently, very deep convolutional neural networks (CNNs) have been attracting considerable attention in image restoration. However, as the depth grows, the long-term dependency problem is rarely realized for these very deep models, which results in the prior states/layers having little influence on the subsequent ones. Motivated by the fact that human thoughts have persistency, we propose a very deep persistent memory network (MemNet) that introduces a memory block, consisting of a recursive unit and a gate unit, to explicitly mine persistent memory through an adaptive learning process. The recursive unit learns multi-level representations of the current state under different receptive fields. The representations and the outputs from the previous memory blocks are concatenated and sent to the gate unit, which adaptively controls how much of the previous states should be reserved, and decides how much of the current state should be stored. We apply MemNet to three image restoration tasks, i.e., image denosing, superresolution and JPEG deblocking. Comprehensive experiments demonstrate the necessity of the MemNet and its unanimous superiority on all three tasks over the state of the arts. Code is available at https://github.com/ tyshiwo/MemNet.
translated by 谷歌翻译
While deep convolutional neural networks (CNNs) have achieved impressive success in image denoising with additive white Gaussian noise (AWGN), their performance remains limited on real-world noisy photographs. The main reason is that their learned models are easy to overfit on the simplified AWGN model which deviates severely from the complicated real-world noise model. In order to improve the generalization ability of deep CNN denoisers, we suggest training a convolutional blind denoising network (CBDNet) with more realistic noise model and real-world noisy-clean image pairs. On the one hand, both signaldependent noise and in-camera signal processing pipeline is considered to synthesize realistic noisy images. On the other hand, real-world noisy photographs and their nearly noise-free counterparts are also included to train our CBD-Net. To further provide an interactive strategy to rectify denoising result conveniently, a noise estimation subnetwork with asymmetric learning to suppress under-estimation of noise level is embedded into CBDNet. Extensive experimental results on three datasets of real-world noisy photographs clearly demonstrate the superior performance of CBDNet over state-of-the-arts in terms of quantitative metrics and visual quality. The code has been made available at https://github.com/GuoShi28/CBDNet.
translated by 谷歌翻译
最近,基于深度学习的图像降级方法在测试数据上具有与训练集相同的测试数据的有希望的性能,在该数据中,已经学习了基于合成或收集的现实世界训练数据的各种denoising模型。但是,在处理真实世界的嘈杂图像时,Denoising的性能仍然受到限制。在本文中,我们提出了一种简单而有效的贝叶斯深集合(BDE)方法,用于真实世界图像denoising,其中可以融合使用各种训练数据设置进行预训练的几位代表性的深层Denoiser,以提高稳健性。 BDE的基础是,现实世界的图像噪声高度取决于信号依赖性,并且在现实世界中的嘈杂图像中的异质噪声可以由不同的Deoisiser分别处理。特别是,我们将受过良好训练的CBDNET,NBNET,HINET,UFORFORMER和GMSNET进入Denoiser池,并采用U-NET来预测Pixel的加权图以融合这些DeOisiser。引入了贝叶斯深度学习策略,而不是仅仅学习像素的加权地图,而是为了预测加权不确定性和加权图,可以通过该策略来建模预测差异,以改善现实世界中的嘈杂图像的鲁棒性。广泛的实验表明,可以通过融合现有的DINOISER而不是训练一个以昂贵的成本来训练一个大的Denoiser来更好地消除现实世界的噪音。在DND数据集上,我们的BDE实现了 +0.28〜dB PSNR的增益,而不是最先进的denoising方法。此外,我们注意到,在应用于现实世界嘈杂的图像时,基于不同高斯噪声水平的BDE Denoiser优于最先进的CBDNET。此外,我们的BDE可以扩展到其他图像恢复任务,并在基准数据集上获得 +0.30dB, +0.18dB和 +0.12dB PSNR的收益,以分别用于图像去除图像,图像降低和单个图像超级分辨率。
translated by 谷歌翻译
最近,卷积神经网络(CNN)已被广泛用于图像DeNoising。现有方法受益于剩余学习并获得高性能。许多研究都注意到优化CNN的网络体系结构,但忽略了残留学习的局限性。本文提出了两个局限性。一个是残留学习的重点是估计噪声,从而忽略图像信息。另一个是图像自相似性没有被有效考虑。本文提出了一个组成剥落网络(CDN),其图像信息路径(IIP)和噪声估计路径(NEP)将分别解决这两个问题。 IIP通过图像到图像的方法来培训图像信息。对于NEP,它从训练的角度利用了图像自相似性。这种基于相似性的训练方法将NEP限制为输出具有特定类型噪声的不同图像贴片的相似估计噪声分布。最后,将全面考虑图像信息和噪声分布信息,以进行图像denoising。实验表明,CDN达到最新的结果会导致合成和现实世界图像降解。我们的代码将在https://github.com/jiahongz/cdn上发布。
translated by 谷歌翻译
We propose a deep learning method for single image superresolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural network (CNN) [15] that takes the lowresolution image as the input and outputs the high-resolution one. We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network. But unlike traditional methods that handle each component separately, our method jointly optimizes all layers. Our deep CNN has a lightweight structure, yet demonstrates state-of-the-art restoration quality, and achieves fast speed for practical on-line usage.
translated by 谷歌翻译
基于深度学习的高光谱图像(HSI)恢复方法因其出色的性能而广受欢迎,但每当任务更改的细节时,通常都需要昂贵的网络再培训。在本文中,我们建议使用有效的插入方法以统一的方法恢复HSI,该方法可以共同保留基于优化方法的灵活性,并利用深神经网络的强大表示能力。具体而言,我们首先开发了一个新的深HSI DeNoiser,利用了门控复发单元,短期和长期的跳过连接以及增强的噪声水平图,以更好地利用HSIS内丰富的空间光谱信息。因此,这导致在高斯和复杂的噪声设置下,在HSI DeNosing上的最新性能。然后,在处理各种HSI恢复任务之前,将提议的DeNoiser插入即插即用的框架中。通过对HSI超分辨率,压缩感测和内部进行的广泛实验,我们证明了我们的方法经常实现卓越的性能,这与每个任务上的最先进的竞争性或甚至更好任何特定任务的培训。
translated by 谷歌翻译
Deconvolution is a widely used strategy to mitigate the blurring and noisy degradation of hyperspectral images~(HSI) generated by the acquisition devices. This issue is usually addressed by solving an ill-posed inverse problem. While investigating proper image priors can enhance the deconvolution performance, it is not trivial to handcraft a powerful regularizer and to set the regularization parameters. To address these issues, in this paper we introduce a tuning-free Plug-and-Play (PnP) algorithm for HSI deconvolution. Specifically, we use the alternating direction method of multipliers (ADMM) to decompose the optimization problem into two iterative sub-problems. A flexible blind 3D denoising network (B3DDN) is designed to learn deep priors and to solve the denoising sub-problem with different noise levels. A measure of 3D residual whiteness is then investigated to adjust the penalty parameters when solving the quadratic sub-problems, as well as a stopping criterion. Experimental results on both simulated and real-world data with ground-truth demonstrate the superiority of the proposed method.
translated by 谷歌翻译
经典图像恢复算法使用各种前瞻性,无论是明确的还是明确的。他们的前沿是手工设计的,它们的相应权重是启发式分配的。因此,深度学习方法通​​常会产生优异的图像恢复质量。然而,深度网络是能够诱导强烈且难以预测的幻觉。在学习图像时,网络隐含地学会联合忠于观察到的数据;然后是不可能的原始数据和下游的幻觉数据的分离。这限制了它们在图像恢复中的广泛采用。此外,通常是降解模型过度装备的受害者的幻觉部分。我们提出了一种具有解耦的网络先前的幻觉和数据保真度的方法。我们将我们的框架称为贝叶斯队的生成先前(BigPrior)的集成。我们的方法植根于贝叶斯框架中,并将其紧密连接到经典恢复方法。实际上,它可以被视为大型经典恢复算法的概括。我们使用网络反转来从生成网络中提取图像先前信息。我们表明,在图像着色,染色和去噪,我们的框架始终如一地提高了反演结果。我们的方法虽然部分依赖于生成网络反演的质量,具有竞争性的监督和任务特定的恢复方法。它还提供了一种额外的公制,其阐述了每像素的先前依赖程度相对于数据保真度。
translated by 谷歌翻译
现实世界图像Denoising是一个实用的图像恢复问题,旨在从野外嘈杂的输入中获取干净的图像。最近,Vision Transformer(VIT)表现出强大的捕获远程依赖性的能力,许多研究人员试图将VIT应用于图像DeNosing任务。但是,现实世界的图像是一个孤立的框架,它使VIT构建了内部贴片的远程依赖性,该依赖性将图像分为贴片并混乱噪声模式和梯度连续性。在本文中,我们建议通过使用连续的小波滑动转换器来解决此问题,该小波滑动转换器在现实世界中构建频率对应关系,称为dnswin。具体而言,我们首先使用CNN编码器从嘈杂的输入图像中提取底部功能。 DNSWIN的关键是将高频和低频信息与功能和构建频率依赖性分开。为此,我们提出了小波滑动窗口变压器,该变压器利用离散的小波变换,自我注意力和逆离散小波变换来提取深度特征。最后,我们使用CNN解码器将深度特征重建为DeNo的图像。对现实世界的基准测试的定量和定性评估都表明,拟议的DNSWIN对最新方法的表现良好。
translated by 谷歌翻译
深卷积神经网络(CNN)用于图像通过自动挖掘精确的结构信息进行图像。但是,大多数现有的CNN依赖于扩大设计网络的深度以获得更好的降级性能,这可能会导致训练难度。在本文中,我们通过三个阶段(即动态卷积块(DCB),两个级联的小波变换和增强块(网络)和残留块(RB)(RB)(RB)(RB),提出了带有小波变换(MWDCNN)的多阶段图像。 。 DCB使用动态卷积来动态调整几次卷积的参数,以在降级性能和计算成本之间做出权衡。 Web使用信号处理技术(即小波转换)和判别性学习的组合来抑制噪声,以恢复图像Denoising中更详细的信息。为了进一步删除冗余功能,RB用于完善获得的功能,以改善通过改进残留密度架构来重建清洁图像的特征。实验结果表明,在定量和定性分析方面,提出的MWDCNN优于一些流行的非授权方法。代码可在https://github.com/hellloxiaotian/mwdcnn上找到。
translated by 谷歌翻译
非盲折叠是一个不良问题。大多数现有方法通常将该问题与最大-A-Bouthiori框架制定,并通过设计潜在清晰图像的类型的正则化术语和数据项来解决它。在本文中,我们通过学习鉴别性收缩函数来提出有效的非盲折叠方法来隐含地模拟这些术语。与使用深度卷积神经网络(CNNS)或径向基函数的大多数现有方法来说,我们简单地学习正则化术语,我们制定数据项和正则化术语,并将解构模型分成与数据相关和正则化相关的子 - 根据乘法器的交替方向方法问题。我们探讨了Maxout函数的属性,并使用颤扬层开发一个深入的CNN模型,以学习直接近似对这两个子问题的解决方案的判别缩小功能。此外,考虑到基于快速的傅里叶变换的图像恢复通常导致振铃伪像,而基于共轭梯度的图像恢复是耗时的,我们开发共轭梯度网络以有效且有效地恢复潜在的清晰图像。实验结果表明,该方法在效率和准确性方面对最先进的方法有利地执行。
translated by 谷歌翻译
图像恢复仍然是图像处理中有挑战性的任务。许多方法解决这个问题,通常通过最小化非平滑惩罚的共轨似然函数来解决。虽然解决方案很容易以理论保证来解释,但其估计依赖于可能需要时间的优化过程。考虑到图像分类和分割深度学习的研究努力,这类方法提供了一个严重的替代方案来执行图像恢复,但要挑战解决逆问题。在这项工作中,我们设计了一个名为Deeppdnet的深网络,从原始双近迭代构建,与之前的分析有关的标准惩罚可能性,允许我们利用两个世界。我们用固定图层为深度网络进行重构Condat-Vu原始 - 双混梯度(PDHG)算法的特定实例。学习的参数均为PDHG算法阶梯大小和惩罚中涉及的分析线性运算符(包括正则化参数)。允许这些参数从层变为另一个参数。提出了两种不同的学习策略:提出了“全学习”和“部分学习”,第一个是数值最有效的,而第二个是依赖于标准约束确保标准PDHG迭代中的收敛。此外,研究了全局和局部稀疏分析,以寻求更好的特征表示。我们将所提出的方法应用于MNIST和BSD68数据集上的图像恢复以及BSD100和SET14数据集的单个图像超分辨率。广泛的结果表明,建议的DeepPDNET在MNIST和更复杂的BSD68,BSD100和SET14数据集中展示了卓越的性能,用于图像恢复和单图像超分辨率任务。
translated by 谷歌翻译
虽然最近基于模型的盲目单图像超分辨率(SISR)的研究已经取得了巨大的成功,但大多数人都不认为图像劣化。首先,它们总是假设图像噪声obeys独立和相同分布的(i.i.d.)高斯或拉普拉斯分布,这在很大程度上低估了真实噪音的复杂性。其次,以前的常用核前沿(例如,归一化,稀疏性)不足以保证理性内核解决方案,从而退化后续SISR任务的性能。为了解决上述问题,本文提出了一种基于模型的盲人SISR方法,该方法在概率框架下,从噪声和模糊内核的角度精心模仿图像劣化。具体而言,而不是传统的i.i.d.噪声假设,基于补丁的非i.i.d。提出噪声模型来解决复杂的真实噪声,期望增加噪声表示模型的自由度。至于模糊内核,我们新建构建一个简洁但有效的内核生成器,并将其插入所提出的盲人SISR方法作为明确的内核(EKP)。为了解决所提出的模型,专门设计了理论上接地的蒙特卡罗EM算法。综合实验证明了我们对综合性和实时数据集的最新技术的方法的优越性。
translated by 谷歌翻译