盲目解构是一种在各种田地中产生的不良问题,从显微镜到天文学。问题的不良性质需要足够的前沿到达理想的解决方案。最近,已经表明,深度学习架构可以用作在无监督盲卷积优化期间的图像生成,然而甚至在单个图像上也呈现性能波动。我们建议使用Wiener-Deconvolulation在优化期间通过从高斯开始使用辅助内核估计来指导图像发生器在优化期间。我们观察到与低频特征相比,通过延迟再现去卷积的高频伪影。另外,图像发生器从模糊图像的速度再现解码图像的低频特征。我们在约束的优化框架中嵌入计算过程,并表明该方法在多个数据集中产生更高的稳定性和性能。此外,我们提供代码。
translated by 谷歌翻译
在计算机视觉和邻近字段中,已广泛研究了盲图片脱毛(BID)。投标的现代方法可以分为两类:使用统计推断和数值优化处理单个实例的单个实体方法,以及数据驱动的方法,这些方法可以直接训练深度学习模型来直接删除未来实例。数据驱动的方法可以摆脱得出准确的模型模型的困难,但从根本上受到培训数据的多样性和质量的限制 - 收集足够表达和现实的培训数据是一个坚定的挑战。在本文中,我们专注于保持竞争力和必不可少的单一稳定方法。但是,大多数此类方法没有规定如何处理未知内核大小和实质性噪音,从而排除了实际部署。实际上,我们表明,当核大小被明确指定时,几种最新的(SOTA)单位方法是不稳定的,并且/或噪声水平很高。从积极的一面来看,我们提出了一种实用的出价方法,该方法对这两者都是稳定的,这是同类的。我们的方法建立在最新的思想,即通过整合物理模型和结构深度神经网络而没有额外的培训数据来解决反问题。我们引入了几种关键修改以实现所需的稳定性。与SOTA单位结构以及数据驱动的方法相比,对标准合成数据集以及现实世界中的NTIRE2020和REALBLUR数据集进行了广泛的经验测试。我们方法的代码可在:\ url {https://github.com/sun-unm/blind-image-deblurring}中获得。
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
在这项工作中,我们研究了非盲目图像解卷积的问题,并提出了一种新的经常性网络架构,其导致高图像质量的竞争性恢复结果。通过现有大规模线性求解器的计算效率和稳健性的推动,我们设法将该问题的解决方案表达为一系列自适应非负数最小二乘问题的解决方案。这引发了我们提出的复发性最小二乘因解网络(RLSDN)架构,其包括在其输入和输出之间施加线性约束的隐式层。通过设计,我们的网络管理以同时服务两个重要的目的。首先,它隐含地模拟了可以充分表征这组自然图像的有效图像,而第二种是它恢复相应的最大后验(MAP)估计。近期最先进的方法的公开数据集的实验表明,我们提出的RLSDN方法可以实现所有测试方案的灰度和彩色图像的最佳报告性能。此外,我们介绍了一种新颖的培训策略,可以通过任何网络架构采用,这些架构涉及线性系统作为其管道的一部分的解决方案。我们的策略完全消除了线性求解器所需迭代的需要,因此,它在训练期间显着降低了内存占用。因此,这使得能够培训更深的网络架构,这可以进一步提高重建结果。
translated by 谷歌翻译
近年来,基于神经网络的深度恢复方法已实现了最先进的方法,从而导致了各种图像过度的任务。但是,基于深度学习的Deblurring网络的一个主要缺点是,训练需要大量模糊清洁图像对才能实现良好的性能。此外,当测试过程中的模糊图像和模糊内核与训练过程中使用的图像和模糊内核时,深层网络通常无法表现良好。这主要是因为网络参数在培训数据上过度拟合。在这项工作中,我们提出了一种解决这些问题的方法。我们将非盲图像脱毛问题视为一个脱氧问题。为此,我们在一对模糊图像上使用相应的模糊内核进行Wiener过滤。这导致一对具有彩色噪声的图像。因此,造成造成的问题被转化为一个降解问题。然后,我们在不使用明确的清洁目标图像的情况下解决了降解问题。进行了广泛的实验,以表明我们的方法取得了与最先进的非盲人脱毛作品相提并论的结果。
translated by 谷歌翻译
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.
translated by 谷歌翻译
Defocus Blur是大多数相机中使用的光学传感器的物理后果。尽管它可以用作摄影风格,但通常被视为图像降解,以形成模型的尖锐图像,并具有空间变化的模糊内核。在过去几年的模糊估计方法的推动下,我们提出了一种非盲方法来处理图像脱毛的方法,可以处理空间变化的核。我们介绍了两个编码器子网络网络,它们分别用模糊图像和估计的模糊图,并作为输出作为输出(Deconvolved)图像的输出。每个子网络都会呈现几个跳过连接,这些连接允许分开分开的数据传播,还可以通过划线跳过连接,以简化模块之间的通信。该网络经过合成的模糊内核训练,这些核被增强以模拟现有模糊估计方法产生的模糊图,我们的实验结果表明,当与多种模糊估计方法结合使用时,我们的方法很好地工作。
translated by 谷歌翻译
在弱光环境下,手持式摄影在长时间的曝光设置下遭受了严重的相机震动。尽管现有的Deblurry算法在暴露良好的模糊图像上表现出了令人鼓舞的性能,但它们仍然无法应对低光快照。在实用的低光脱毛中,复杂的噪声和饱和区是两个主导挑战。在这项工作中,我们提出了一种称为图像的新型非盲脱毛方法,并具有特征空间Wiener Deonervolution网络(Infwide),以系统地解决这些问题。在算法设计方面,Infwide提出了一个两分支的架构,该体系结构明确消除了噪声并幻觉,使图像空间中的饱和区域抑制了特征空间中的响起文物,并将两个互补输出与一个微妙的多尺度融合网络集成在一起高质量的夜间照片浮雕。为了进行有效的网络培训,我们设计了一组损失功能,集成了前向成像模型和向后重建,以形成近环的正则化,以确保深神经网络的良好收敛性。此外,为了优化Infwide在实际弱光条件下的适用性,采用基于物理过程的低光噪声模型来合成现实的嘈杂夜间照片进行模型训练。利用传统的Wiener Deonervolution算法的身体驱动的特征并引起了深层神经网络的表示能力,Infwide可以恢复细节,同时抑制在脱毛期间的不愉快的人工制品。关于合成数据和实际数据的广泛实验证明了所提出的方法的出色性能。
translated by 谷歌翻译
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。
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
在本文中,我们考虑了Defocus图像去缩合中的问题。以前的经典方法遵循两步方法,即首次散焦映射估计,然后是非盲目脱毛。在深度学习时代,一些研究人员试图解决CNN的这两个问题。但是,代表模糊级别的Defocus图的简单串联导致了次优性能。考虑到Defocus Blur的空间变体特性和Defocus Map中指示的模糊级别,我们采用Defocus Map作为条件指导来调整输入模糊图像而不是简单串联的特征。然后,我们提出了一个基于Defocus图的空间调制的简单但有效的网络。为了实现这一目标,我们设计了一个由三个子网络组成的网络,包括DeFocus Map估计网络,该网络将DeFocus Map编码为条件特征的条件网络以及根据条件功能执行空间动态调制的DeFocus Deblurring网络。此外,空间动态调制基于仿射变换函数,以调整输入模糊图像的特征。实验结果表明,与常用的公共测试数据集中的现有最新方法相比,我们的方法可以实现更好的定量和定性评估性能。
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
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
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
translated by 谷歌翻译
Recent image degradation estimation methods have enabled single-image super-resolution (SR) approaches to better upsample real-world images. Among these methods, explicit kernel estimation approaches have demonstrated unprecedented performance at handling unknown degradations. Nonetheless, a number of limitations constrain their efficacy when used by downstream SR models. Specifically, this family of methods yields i) excessive inference time due to long per-image adaptation times and ii) inferior image fidelity due to kernel mismatch. In this work, we introduce a learning-to-learn approach that meta-learns from the information contained in a distribution of images, thereby enabling significantly faster adaptation to new images with substantially improved performance in both kernel estimation and image fidelity. Specifically, we meta-train a kernel-generating GAN, named MetaKernelGAN, on a range of tasks, such that when a new image is presented, the generator starts from an informed kernel estimate and the discriminator starts with a strong capability to distinguish between patch distributions. Compared with state-of-the-art methods, our experiments show that MetaKernelGAN better estimates the magnitude and covariance of the kernel, leading to state-of-the-art blind SR results within a similar computational regime when combined with a non-blind SR model. Through supervised learning of an unsupervised learner, our method maintains the generalizability of the unsupervised learner, improves the optimization stability of kernel estimation, and hence image adaptation, and leads to a faster inference with a speedup between 14.24 to 102.1x over existing methods.
translated by 谷歌翻译
Deep convolutional networks have become a popular tool for image generation and restoration. Generally, their excellent performance is imputed to their ability to learn realistic image priors from a large number of example images. In this paper, we show that, on the contrary, the structure of a generator network is sufficient to capture a great deal of low-level image statistics prior to any learning. In order to do so, we show that a randomly-initialized neural network can be used as a handcrafted prior with excellent results in standard inverse problems such as denoising, superresolution, and inpainting. Furthermore, the same prior can be used to invert deep neural representations to diagnose them, and to restore images based on flash-no flash input pairs.
translated by 谷歌翻译
Convolutional Neural Network (CNN)-based image super-resolution (SR) has exhibited impressive success on known degraded low-resolution (LR) images. However, this type of approach is hard to hold its performance in practical scenarios when the degradation process is unknown. Despite existing blind SR methods proposed to solve this problem using blur kernel estimation, the perceptual quality and reconstruction accuracy are still unsatisfactory. In this paper, we analyze the degradation of a high-resolution (HR) image from image intrinsic components according to a degradation-based formulation model. We propose a components decomposition and co-optimization network (CDCN) for blind SR. Firstly, CDCN decomposes the input LR image into structure and detail components in feature space. Then, the mutual collaboration block (MCB) is presented to exploit the relationship between both two components. In this way, the detail component can provide informative features to enrich the structural context and the structure component can carry structural context for better detail revealing via a mutual complementary manner. After that, we present a degradation-driven learning strategy to jointly supervise the HR image detail and structure restoration process. Finally, a multi-scale fusion module followed by an upsampling layer is designed to fuse the structure and detail features and perform SR reconstruction. Empowered by such degradation-based components decomposition, collaboration, and mutual optimization, we can bridge the correlation between component learning and degradation modelling for blind SR, thereby producing SR results with more accurate textures. Extensive experiments on both synthetic SR datasets and real-world images show that the proposed method achieves the state-of-the-art performance compared to existing methods.
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
By adopting popular pixel-wise loss, existing methods for defocus deblurring heavily rely on well aligned training image pairs. Although training pairs of ground-truth and blurry images are carefully collected, e.g., DPDD dataset, misalignment is inevitable between training pairs, making existing methods possibly suffer from deformation artifacts. In this paper, we propose a joint deblurring and reblurring learning (JDRL) framework for single image defocus deblurring with misaligned training pairs. Generally, JDRL consists of a deblurring module and a spatially invariant reblurring module, by which deblurred result can be adaptively supervised by ground-truth image to recover sharp textures while maintaining spatial consistency with the blurry image. First, in the deblurring module, a bi-directional optical flow-based deformation is introduced to tolerate spatial misalignment between deblurred and ground-truth images. Second, in the reblurring module, deblurred result is reblurred to be spatially aligned with blurry image, by predicting a set of isotropic blur kernels and weighting maps. Moreover, we establish a new single image defocus deblurring (SDD) dataset, further validating our JDRL and also benefiting future research. Our JDRL can be applied to boost defocus deblurring networks in terms of both quantitative metrics and visual quality on DPDD, RealDOF and our SDD datasets.
translated by 谷歌翻译
受监管的基于学习的方法屈服于强大的去噪结果,但它们本质上受到大规模清洁/嘈杂配对数据集的需要。另一方面,使用无监督的脱言机需要更详细地了解潜在的图像统计数据。特别是,众所周知,在高频频带上,清洁和嘈杂的图像之间的表观差异是最突出的,证明使用低通滤波器作为传统图像预处理步骤的一部分。然而,基于大多数基于学习的去噪方法在不考虑频域信息的情况下仅利用来自空间域的片面信息。为了解决这一限制,在本研究中,我们提出了一种频率敏感的无监督去噪方法。为此,使用生成的对抗性网络(GaN)作为基础结构。随后,我们包括光谱鉴别器和频率重建损失,以将频率知识传输到发电机中。使用自然和合成数据集的结果表明,我们无监督的学习方法增强了频率信息,实现了最先进的去噪能力,表明频域信息可能是提高无监督基于学习的方法的整体性能的可行因素。
translated by 谷歌翻译