在本文中，我们介绍了一种快速运动脱棕色条件的生成对抗网络（FMD-CGAN），其有助于单个图像的盲运动去纹理。 FMD-CGAN在去修改图像后提供令人印象深刻的结构相似性和视觉外观。与其他深度神经网络架构一样，GAN也遭受大型模型大小（参数）和计算。在诸如移动设备和机器人等资源约束设备上部署模型并不容易。借助MobileNet基于MobileNet的架构，包括深度可分离卷积，我们降低了模型大小和推理时间，而不会丢失图像的质量。更具体地说，我们将模型大小与最近的竞争对手相比将3-60倍。由此产生的压缩去掩盖CGAN比其最接近的竞争对手更快，甚至定性和定量结果优于各种最近提出的最先进的盲运动去误紧模型。我们还可以使用我们的模型进行实时映像解擦干任务。标准数据集的当前实验显示了该方法的有效性。

We present DeblurGAN, an end-to-end learned method for motion deblurring. The learning is based on a conditional GAN and the content loss . DeblurGAN achieves state-of-the art performance both in the structural similarity measure and visual appearance. The quality of the deblurring model is also evaluated in a novel way on a real-world problem -object detection on (de-)blurred images. The method is 5 times faster than the closest competitor -Deep-Deblur [25]. We also introduce a novel method for generating synthetic motion blurred images from sharp ones, allowing realistic dataset augmentation.The model, code and the dataset are available at https://github.com/KupynOrest/DeblurGAN

We present a new end-to-end generative adversarial network (GAN) for single image motion deblurring, named DeblurGAN-v2, which considerably boosts state-of-the-art deblurring efficiency, quality, and flexibility. DeblurGAN-v2 is based on a relativistic conditional GAN with a doublescale discriminator. For the first time, we introduce the Feature Pyramid Network into deblurring, as a core building block in the generator of DeblurGAN-v2. It can flexibly work with a wide range of backbones, to navigate the balance between performance and efficiency. The plugin of sophisticated backbones (e.g., Inception-ResNet-v2) can lead to solid state-of-the-art deblurring. Meanwhile, with light-weight backbones (e.g., MobileNet and its variants), DeblurGAN-v2 reaches 10-100 times faster than the nearest competitors, while maintaining close to state-ofthe-art results, implying the option of real-time video deblurring. We demonstrate that DeblurGAN-v2 obtains very competitive performance on several popular benchmarks, in terms of deblurring quality (both objective and subjective), as well as efficiency. Besides, we show the architecture to be effective for general image restoration tasks too. Our codes, models and data are available at: https: //github.com/KupynOrest/DeblurGANv2.

在本文中，我们介绍了基于稀疏学习的端到端生成的对抗网络（GAN），用于单幅图像盲运动去纹理，我们称为SL-Corpygan。在盲运运动去纹理中的第一次，我们提出了一种稀疏的Reset-块作为基于HTM（分层时间内存）的稀疏卷积层和可训练的空间池K-Winner的组合，以替换RESET中的非线性等非线性-Block的SL-Corpergan发电机。此外，与许多最先进的GaN的运动脱孔方法不同，将运动脱棕色作为线性端到端过程，我们从CompyGan的域名翻译能力中获取灵感，我们展示图像去孔可以是循环一致的，同时实现最佳定性结果。最后，我们在定性和定量上对流行的图像基准进行了广泛的实验，并在GoPro数据集上实现了38.087 dB的记录分布PSNR，比最新的去纹理方法优于5.377 dB。

Non-uniform blind deblurring for general dynamic scenes is a challenging computer vision problem as blurs arise not only from multiple object motions but also from camera shake, scene depth variation. To remove these complicated motion blurs, conventional energy optimization based methods rely on simple assumptions such that blur kernel is partially uniform or locally linear. Moreover, recent machine learning based methods also depend on synthetic blur datasets generated under these assumptions. This makes conventional deblurring methods fail to remove blurs where blur kernel is difficult to approximate or parameterize (e.g. object motion boundaries). In this work, we propose a multi-scale convolutional neural network that restores sharp images in an end-to-end manner where blur is caused by various sources. Together, we present multiscale loss function that mimics conventional coarse-to-fine approaches. Furthermore, we propose a new large-scale dataset that provides pairs of realistic blurry image and the corresponding ground truth sharp image that are obtained by a high-speed camera. With the proposed model trained on this dataset, we demonstrate empirically that our method achieves the state-of-the-art performance in dynamic scene deblurring not only qualitatively, but also quantitatively.

我们引入了一个新颖的框架，用于连续的面部运动脱毛，该框架通过矩控制因子恢复单个运动毛面脸部图像中潜在的连续锋利力矩。尽管动作毛刺图像是在曝光时间内连续锋利矩的累积信号，但大多数现有的单个图像脱毛方法旨在使用多个网络和训练阶段恢复固定数量的帧。为了解决这个问题，我们提出了一个基于GAN（CFMD-GAN）的连续面部运动脱毛网络，该网络是一个新颖的框架，用于恢复带有单个网络和单个训练阶段的单个运动型面部图像中潜在的连续力矩。为了稳定网络培训，我们训练发电机以通过面部特定于面部知识的面部基于面部运动的重新排序过程（FMR）确定的顺序恢复连续矩。此外，我们提出了一个辅助回归器，该回归器通过估计连续锋利的力矩来帮助我们的发电机产生更准确的图像。此外，我们引入了一个控制自适应（CONTADA）块，该块执行空间变形的卷积和频道的注意，作为控制因子的函数。 300VW数据集上的大量实验表明，所提出的框架通过改变力矩控制因子来生成各种连续的输出帧。与最近使用相同300VW训练集训练的最近的单一单击图像脱蓝色网络相比，提出的方法显示了在感知指标（包括LPIPS，FID和Arcface身份距离）方面恢复中央锋利框架的出色性能。该方法的表现优于现有的单一视频脱蓝和用于定性和定量比较的方法。

近年来，使用基于深入学习的架构的状态，在图像超分辨率的任务中有几个进步。先前发布的许多基于超分辨率的技术，需要高端和顶部的图形处理单元（GPU）来执行图像超分辨率。随着深度学习方法的进步越来越大，神经网络已经变得越来越多地计算饥饿。我们返回了一步，并专注于创建实时有效的解决方案。我们提出了一种在其内存足迹方面更快更小的架构。所提出的架构使用深度明智的可分离卷积来提取特征，并且它与其他超分辨率的GAN（生成对抗网络）进行接受，同时保持实时推断和低存储器占用。即使在带宽条件不佳，实时超分辨率也能够流式传输高分辨率介质内容。在维持准确性和延迟之间的有效权衡之间，我们能够生产可比较的性能模型，该性能模型是超分辨率GAN的大小的一个 - 八（1/8），并且计算的速度比超分辨率的GAN快74倍。

Single image super-resolution is the task of inferring a high-resolution image from a single low-resolution input. Traditionally, the performance of algorithms for this task is measured using pixel-wise reconstruction measures such as peak signal-to-noise ratio (PSNR) which have been shown to correlate poorly with the human perception of image quality. As a result, algorithms minimizing these metrics tend to produce over-smoothed images that lack highfrequency textures and do not look natural despite yielding high PSNR values.We propose a novel application of automated texture synthesis in combination with a perceptual loss focusing on creating realistic textures rather than optimizing for a pixelaccurate reproduction of ground truth images during training. By using feed-forward fully convolutional neural networks in an adversarial training setting, we achieve a significant boost in image quality at high magnification ratios. Extensive experiments on a number of datasets show the effectiveness of our approach, yielding state-of-the-art results in both quantitative and qualitative benchmarks.

在文献中，粗细或缩放 - 重复性方法是从其低分辨率版本逐步恢复清洁图像，已成功用于单图像去孔。然而，现有方法的主要缺点是需要配对数据;即夏普尔图像对同一场景，这是一种复杂和繁琐的采集程序。此外，由于对损耗功能的强烈监督，此类网络的预先训练模型对训练期间的模糊强烈偏向，并且在推理时间内的新模糊内核面对时倾向于提供子最佳性能。为了解决上述问题，我们使用秤 - 自适应注意模块（Saam）提出了无监督的域特定的去孔。我们的网络不需要监督对进行训练，并且防夹机制主要由逆势丢失引导，从而使我们的网络适用于模糊功能的分布。给定模糊的输入图像，在训练期间我们的模型中使用相同图像的不同分辨率，Saam允许在整个分辨率上有效的信息流。对于特定规模的网络培训，Saam作为当前规模的函数参加较低的尺度功能。不同的消融研究表明，我们的粗细机制优于端到端无监督的模型，而Saam能够与文学中使用的注意力相比更好地参加。定性和定量比较（在无参考度量标准）表明我们的方法优于现有无监督的方法。

本文提出了一种有效融合多暴露输入并使用未配对数据集生成高质量的高动态范围（HDR）图像的方法。基于深度学习的HDR图像生成方法在很大程度上依赖于配对的数据集。地面真相图像在生成合理的HDR图像中起着领导作用。没有地面真理的数据集很难应用于训练深层神经网络。最近，在没有配对示例的情况下，生成对抗网络（GAN）证明了它们将图像从源域X转换为目标域y的潜力。在本文中，我们提出了一个基于GAN的网络，用于解决此类问题，同时产生愉快的HDR结果，名为Uphdr-Gan。提出的方法放松了配对数据集的约束，并了解了从LDR域到HDR域的映射。尽管丢失了这些对数据，但UPHDR-GAN可以借助修改后的GAN丢失，改进的歧视器网络和有用的初始化阶段正确处理由移动对象或未对准引起的幽灵伪像。所提出的方法保留了重要区域的细节并提高了总图像感知质量。与代表性方法的定性和定量比较证明了拟议的UPHDR-GAN的优越性。

Despite deep end-to-end learning methods have shown their superiority in removing non-uniform motion blur, there still exist major challenges with the current multi-scale and scale-recurrent models: 1) Deconvolution/upsampling operations in the coarse-to-fine scheme result in expensive runtime; 2) Simply increasing the model depth with finer-scale levels cannot improve the quality of deblurring. To tackle the above problems, we present a deep hierarchical multi-patch network inspired by Spatial Pyramid Matching to deal with blurry images via a fine-tocoarse hierarchical representation. To deal with the performance saturation w.r.t. depth, we propose a stacked version of our multi-patch model. Our proposed basic multi-patch model achieves the state-of-the-art performance on the Go-Pro dataset while enjoying a 40× faster runtime compared to current multi-scale methods. With 30ms to process an image at 1280×720 resolution, it is the first real-time deep motion deblurring model for 720p images at 30fps. For stacked networks, significant improvements (over 1.2dB) are achieved on the GoPro dataset by increasing the network depth. Moreover, by varying the depth of the stacked model, one can adapt the performance and runtime of the same network for different application scenarios.

The Super-Resolution Generative Adversarial Network (SR-GAN) [1] is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied with unpleasant artifacts. To further enhance the visual quality, we thoroughly study three key components of SRGANnetwork architecture, adversarial loss and perceptual loss, and improve each of them to derive an Enhanced SRGAN (ESRGAN). In particular, we introduce the Residual-in-Residual Dense Block (RRDB) without batch normalization as the basic network building unit. Moreover, we borrow the idea from relativistic GAN [2] to let the discriminator predict relative realness instead of the absolute value. Finally, we improve the perceptual loss by using the features before activation, which could provide stronger supervision for brightness consistency and texture recovery. Benefiting from these improvements, the proposed ESRGAN achieves consistently better visual quality with more realistic and natural textures than SRGAN and won the first place in the PIRM2018-SR Challenge 1 [3]. The code is available at https://github.com/xinntao/ESRGAN.

近年来已经提出了显示屏下的显示器，作为减少移动设备的形状因子的方式，同时最大化屏幕区域。不幸的是，将相机放在屏幕后面导致显着的图像扭曲，包括对比度，模糊，噪音，色移，散射伪像和降低光敏性的损失。在本文中，我们提出了一种图像恢复管道，其是ISP-Annostic，即它可以与任何传统ISP组合，以产生使用相同的ISP与常规相机外观匹配的最终图像。这是通过执行Raw-Raw Image Restoration的深度学习方法来实现的。为了获得具有足够对比度和场景多样性的大量实际展示摄像机培训数据，我们还开发利用HDR监视器的数据捕获方法，以及数据增强方法以产生合适的HDR内容。监视器数据补充有现实世界的数据，该数据具有较少的场景分集，但允许我们实现细节恢复而不受监视器分辨率的限制。在一起，这种方法成功地恢复了颜色和对比度以及图像细节。

夜间摄影通常由于昏暗的环境和长期使用而遭受弱光和模糊问题。尽管现有的光增强和脱毛方法可以单独解决每个问题，但一系列此类方法不能和谐地适应可见性和纹理的共同降解。训练端到端网络也是不可行的，因为没有配对数据可以表征低光和模糊的共存。我们通过引入新的数据合成管道来解决该问题，该管道对现实的低光模糊降解进行建模。使用管道，我们介绍了第一个用于关节低光增强和去皮的大型数据集。数据集，LOL-BLUR，包含12,000个低Blur/正常出现的对，在不同的情况下具有不同的黑暗和运动模糊。我们进一步提出了一个名为LEDNET的有效网络，以执行关节弱光增强和脱毛。我们的网络是独一无二的，因为它是专门设计的，目的是考虑两个相互连接的任务之间的协同作用。拟议的数据集和网络都为这项具有挑战性的联合任务奠定了基础。广泛的实验证明了我们方法对合成和现实数据集的有效性。

Multi-Scale and U-shaped Networks are widely used in various image restoration problems, including deblurring. Keeping in mind the wide range of applications, we present a comparison of these architectures and their effects on image deblurring. We also introduce a new block called as NFResblock. It consists of a Fast Fourier Transformation layer and a series of modified Non-Linear Activation Free Blocks. Based on these architectures and additions, we introduce NFResnet and NFResnet+, which are modified multi-scale and U-Net architectures, respectively. We also use three different loss functions to train these architectures: Charbonnier Loss, Edge Loss, and Frequency Reconstruction Loss. Extensive experiments on the Deep Video Deblurring dataset, along with ablation studies for each component, have been presented in this paper. The proposed architectures achieve a considerable increase in Peak Signal to Noise (PSNR) ratio and Structural Similarity Index (SSIM) value.

使用注意机制的深度卷积神经网络（CNN）在动态场景中取得了巨大的成功。在大多数这些网络中，只能通过注意图精炼的功能传递到下一层，并且不同层的注意力图彼此分开，这并不能充分利用来自CNN中不同层的注意信息。为了解决这个问题，我们引入了一种新的连续跨层注意传播（CCLAT）机制，该机制可以利用所有卷积层的分层注意信息。基于CCLAT机制，我们使用非常简单的注意模块来构建一个新型残留的密集注意融合块（RDAFB）。在RDAFB中，从上述RDAFB的输出中推断出的注意图和每一层直接连接到后续的映射，从而导致CRLAT机制。以RDAFB为基础，我们为动态场景Deblurring设计了一个名为RDAFNET的有效体系结构。基准数据集上的实验表明，所提出的模型的表现优于最先进的脱毛方法，并证明了CCLAT机制的有效性。源代码可在以下网址提供：https：//github.com/xjmz6/rdafnet。

Face Restoration (FR) aims to restore High-Quality (HQ) faces from Low-Quality (LQ) input images, which is a domain-specific image restoration problem in the low-level computer vision area. The early face restoration methods mainly use statistic priors and degradation models, which are difficult to meet the requirements of real-world applications in practice. In recent years, face restoration has witnessed great progress after stepping into the deep learning era. However, there are few works to study deep learning-based face restoration methods systematically. Thus, this paper comprehensively surveys recent advances in deep learning techniques for face restoration. Specifically, we first summarize different problem formulations and analyze the characteristic of the face image. Second, we discuss the challenges of face restoration. Concerning these challenges, we present a comprehensive review of existing FR methods, including prior based methods and deep learning-based methods. Then, we explore developed techniques in the task of FR covering network architectures, loss functions, and benchmark datasets. We also conduct a systematic benchmark evaluation on representative methods. Finally, we discuss future directions, including network designs, metrics, benchmark datasets, applications,etc. We also provide an open-source repository for all the discussed methods, which is available at https://github.com/TaoWangzj/Awesome-Face-Restoration.

图像超分辨率（SR）是重要的图像处理方法之一，可改善计算机视野领域的图像分辨率。在过去的二十年中，在超级分辨率领域取得了重大进展，尤其是通过使用深度学习方法。这项调查是为了在深度学习的角度进行详细的调查，对单像超分辨率的最新进展进行详细的调查，同时还将告知图像超分辨率的初始经典方法。该调查将图像SR方法分类为四个类别，即经典方法，基于学习的方法，无监督学习的方法和特定领域的SR方法。我们还介绍了SR的问题，以提供有关图像质量指标，可用参考数据集和SR挑战的直觉。使用参考数据集评估基于深度学习的方法。一些审查的最先进的图像SR方法包括增强的深SR网络（EDSR），周期循环gan（Cincgan），多尺度残留网络（MSRN），Meta残留密度网络（META-RDN） ，反复反射网络（RBPN），二阶注意网络（SAN），SR反馈网络（SRFBN）和基于小波的残留注意网络（WRAN）。最后，这项调查以研究人员将解决SR的未来方向和趋势和开放问题的未来方向和趋势。

Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture details when we super-resolve at large upscaling factors? The behavior of optimization-based super-resolution methods is principally driven by the choice of the objective function. Recent work has largely focused on minimizing the mean squared reconstruction error. The resulting estimates have high peak signal-to-noise ratios, but they are often lacking high-frequency details and are perceptually unsatisfying in the sense that they fail to match the fidelity expected at the higher resolution. In this paper, we present SRGAN, a generative adversarial network (GAN) for image superresolution (SR). To our knowledge, it is the first framework capable of inferring photo-realistic natural images for 4× upscaling factors. To achieve this, we propose a perceptual loss function which consists of an adversarial loss and a content loss. The adversarial loss pushes our solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images. In addition, we use a content loss motivated by perceptual similarity instead of similarity in pixel space. Our deep residual network is able to recover photo-realistic textures from heavily downsampled images on public benchmarks. An extensive mean-opinion-score (MOS) test shows hugely significant gains in perceptual quality using SRGAN. The MOS scores obtained with SRGAN are closer to those of the original high-resolution images than to those obtained with any state-of-the-art method.

在各种基于学习的图像恢复任务（例如图像降解和图像超分辨率）中，降解表示形式被广泛用于建模降解过程并处理复杂的降解模式。但是，在基于学习的图像deblurring中，它们的探索程度较低，因为在现实世界中挑战性的情况下，模糊内核估计不能很好地表现。我们认为，对于图像降低的降解表示形式是特别必要的，因为模糊模式通常显示出比噪声模式或高频纹理更大的变化。在本文中，我们提出了一个框架来学习模糊图像的空间自适应降解表示。提出了一种新颖的联合图像re毁和脱蓝色的学习过程，以提高降解表示的表现力。为了使学习的降解表示有效地启动和降解，我们提出了一个多尺度退化注入网络（MSDI-NET），以将它们集成到神经网络中。通过集成，MSDI-NET可以适应各种复杂的模糊模式。 GoPro和Realblur数据集上的实验表明，我们提出的具有学识渊博的退化表示形式的Deblurring框架优于最先进的方法，具有吸引人的改进。该代码在https://github.com/dasongli1/learning_degradation上发布。