Generative models learned from training using deep learning methods can be used as priors in inverse under-determined inverse problems, including imaging from sparse set of measurements. In this paper, we present a novel hierarchical deep-generative model MrSARP for SAR imagery that can synthesize SAR images of a target at different resolutions jointly. MrSARP is trained in conjunction with a critic that scores multi resolution images jointly to decide if they are realistic images of a target at different resolutions. We show how this deep generative model can be used to retrieve the high spatial resolution image from low resolution images of the same target. The cost function of the generator is modified to improve its capability to retrieve the input parameters for a given set of resolution images. We evaluate the model's performance using the three standard error metrics used for evaluating super-resolution performance on simulated data and compare it to upsampling and sparsity based image sharpening approaches.
translated by 谷歌翻译
近年来,在诸如denoing,压缩感应,介入和超分辨率等反问题中使用深度学习方法的使用取得了重大进展。尽管这种作品主要是由实践算法和实验驱动的,但它也引起了各种有趣的理论问题。在本文中,我们调查了这一作品中一些突出的理论发展,尤其是生成先验,未经训练的神经网络先验和展开算法。除了总结这些主题中的现有结果外,我们还强调了一些持续的挑战和开放问题。
translated by 谷歌翻译
物理驱动的深度学习方法已成为计算磁共振成像(MRI)问题的强大工具,将重建性能推向新限制。本文概述了将物理信息纳入基于学习的MRI重建中的最新发展。我们考虑了用于计算MRI的线性和非线性正向模型的逆问题,并回顾了解决这些方法的经典方法。然后,我们专注于物理驱动的深度学习方法,涵盖了物理驱动的损失功能,插件方法,生成模型和展开的网络。我们重点介绍了特定于领域的挑战,例如神经网络的实现和复杂值的构建基块,以及具有线性和非线性正向模型的MRI转换应用。最后,我们讨论常见问题和开放挑战,并与物理驱动的学习与医学成像管道中的其他下游任务相结合时,与物理驱动的学习的重要性联系在一起。
translated by 谷歌翻译
自动目标识别(ATR)算法将给定的合成孔径雷达(SAR)图像分类为已知的目标类之一,使用一组可用于每个类的训练图像。最近,如果有丰富的训练数据可用,在类中均匀地采样及其姿势,则已经显示出学习方法可以实现最先进的分类精度。在本文中,我们考虑了ATR的任务,其中一组培训图像有限。我们提出了一种数据增强方法,以结合域知识并提高数据密集型学习算法的概括能力,例如卷积神经网络(CNN)。提出的数据增强方法采用有限的持久性稀疏建模方法,利用广角合成孔径雷达(SAR)图像的普遍观察到的特征。具体而言,我们利用空间结构域中的散射中心的稀疏性以及方位角域中散射系数的平滑结构,以解决过度分析模型拟合的缺陷问题。使用此估计的模型,我们合成了给定数据中没有可用的姿势和子像素翻译的新图像来增强CNN的培训数据。实验结果表明,对于训练数据饥饿的区域,提出的方法为结果ATR算法的泛化性能提供了显着增长。
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
最近,由于高性能,深度学习方法已成为生物学图像重建和增强问题的主要研究前沿,以及其超快速推理时间。但是,由于获得监督学习的匹配参考数据的难度,对不需要配对的参考数据的无监督学习方法越来越兴趣。特别是,已成功用于各种生物成像应用的自我监督的学习和生成模型。在本文中,我们概述了在古典逆问题的背景下的连贯性观点,并讨论其对生物成像的应用,包括电子,荧光和去卷积显微镜,光学衍射断层扫描和功能性神经影像。
translated by 谷歌翻译
The goal of compressed sensing is to estimate a vector from an underdetermined system of noisy linear measurements, by making use of prior knowledge on the structure of vectors in the relevant domain. For almost all results in this literature, the structure is represented by sparsity in a well-chosen basis. We show how to achieve guarantees similar to standard compressed sensing but without employing sparsity at all. Instead, we suppose that vectors lie near the range of a generative model G : R k → R n . Our main theorem is that, if G is L-Lipschitz, then roughly O(k log L) random Gaussian measurements suffice for an 2/ 2 recovery guarantee. We demonstrate our results using generative models from published variational autoencoder and generative adversarial networks. Our method can use 5-10x fewer measurements than Lasso for the same accuracy.
translated by 谷歌翻译
近年来,深度学习在图像重建方面取得了显着的经验成功。这已经促进了对关键用例中数据驱动方法的正确性和可靠性的精确表征的持续追求,例如在医学成像中。尽管基于深度学习的方法具有出色的性能和功效,但对其稳定性或缺乏稳定性的关注以及严重的实际含义。近年来,已经取得了重大进展,以揭示数据驱动的图像恢复方法的内部运作,从而挑战了其广泛认为的黑盒本质。在本文中,我们将为数据驱动的图像重建指定相关的融合概念,该概念将构成具有数学上严格重建保证的学习方法调查的基础。强调的一个例子是ICNN的作用,提供了将深度学习的力量与经典凸正则化理论相结合的可能性,用于设计被证明是融合的方法。这篇调查文章旨在通过提供对数据驱动的图像重建方法以及从业人员的理解,旨在通过提供可访问的融合概念的描述,并通过将一些现有的经验实践放在可靠的数学上,来推进我们对数据驱动图像重建方法的理解以及从业人员的了解。基础。
translated by 谷歌翻译
深度图像先验表明,通过简单地优化它的参数来重建单个降级图像,可以训练具有合适架构的随机初始化网络以解决反向成像问题。但是,它受到了两个实际限制。首先,它仍然不清楚如何在网络架构选择之前控制。其次,培训需要Oracle停止标准,因为在优化期间,在达到最佳值后性能降低。为了解决这些挑战,我们引入频带对应度量以表征在之前的深图像的光谱偏压,其中低频图像信号比高频对应物更快且更好地学习。根据我们的观察,我们提出了防止最终性能下降和加速收敛的技术。我们介绍了Lipschitz受控的卷积层和高斯控制的上采样层,作为深度架构中使用的层的插件替代品。实验表明,随着这些变化,在优化期间,性能不会降低,从需要对Oracle停止标准的需求中脱离我们。我们进一步勾勒出停止标准以避免多余的计算。最后,我们表明我们的方法与各种去噪,去块,染色,超级分辨率和细节增强任务的当前方法相比获得了有利的结果。代码可用于\ url {https:/github.com/shizenglin/measure-and-control-spectraL-bias}。
translated by 谷歌翻译
传统上,信号处理,通信和控制一直依赖经典的统计建模技术。这种基于模型的方法利用代表基本物理,先验信息和其他领域知识的数学公式。简单的经典模型有用,但对不准确性敏感,当真实系统显示复杂或动态行为时,可能会导致性能差。另一方面,随着数据集变得丰富,现代深度学习管道的力量增加,纯粹的数据驱动的方法越来越流行。深度神经网络(DNNS)使用通用体系结构,这些架构学会从数据中运行,并表现出出色的性能,尤其是针对受监督的问题。但是,DNN通常需要大量的数据和巨大的计算资源,从而限制了它们对某些信号处理方案的适用性。我们对将原则数学模型与数据驱动系统相结合的混合技术感兴趣,以从两种方法的优势中受益。这种基于模型的深度学习方法通​​过为特定问题设计的数学结构以及从有限的数据中学习来利用这两个部分领域知识。在本文中,我们调查了研究和设计基于模型的深度学习系统的领先方法。我们根据其推理机制将基于混合模型/数据驱动的系统分为类别。我们对以系统的方式将基于模型的算法与深度学习以及具体指南和详细的信号处理示例相结合的领先方法进行了全面综述。我们的目的是促进对未来系统的设计和研究信号处理和机器学习的交集,这些系统结合了两个领域的优势。
translated by 谷歌翻译
Countless signal processing applications include the reconstruction of signals from few indirect linear measurements. The design of effective measurement operators is typically constrained by the underlying hardware and physics, posing a challenging and often even discrete optimization task. While the potential of gradient-based learning via the unrolling of iterative recovery algorithms has been demonstrated, it has remained unclear how to leverage this technique when the set of admissible measurement operators is structured and discrete. We tackle this problem by combining unrolled optimization with Gumbel reparametrizations, which enable the computation of low-variance gradient estimates of categorical random variables. Our approach is formalized by GLODISMO (Gradient-based Learning of DIscrete Structured Measurement Operators). This novel method is easy-to-implement, computationally efficient, and extendable due to its compatibility with automatic differentiation. We empirically demonstrate the performance and flexibility of GLODISMO in several prototypical signal recovery applications, verifying that the learned measurement matrices outperform conventional designs based on randomization as well as discrete optimization baselines.
translated by 谷歌翻译
机器学习模型通常培训端到端和监督设置,使用配对(输入,输出)数据。示例包括最近的超分辨率方法,用于在(低分辨率,高分辨率)图像上培训。然而,这些端到端的方法每当输入中存在分布偏移时需要重新训练(例如,夜间图像VS日光)或相关的潜在变量(例如,相机模糊或手动运动)。在这项工作中,我们利用最先进的(SOTA)生成模型(这里是Stylegan2)来构建强大的图像前提,这使得贝叶斯定理应用于许多下游重建任务。我们的方法是通过生成模型(BRGM)的贝叶斯重建,使用单个预先训练的发生器模型来解决不同的图像恢复任务,即超级分辨率和绘画,通过与不同的前向腐败模型相结合。我们将发电机模型的重量保持固定,并通过估计产生重建图像的输入潜在的跳过载体来重建图像来估计图像。我们进一步使用变分推理来近似潜伏向量的后部分布,我们对多种解决方案进行采样。我们在三个大型和多样化的数据集中展示了BRGM:(i)来自Flick的60,000个图像面向高质量的数据集(II)来自MIMIC III的高质量数据集(II)240,000胸X射线,(III)的组合收集5脑MRI数据集,具有7,329个扫描。在所有三个数据集和没有任何DataSet特定的HyperParameter调整,我们的简单方法会在超级分辨率和绘画上对当前的特定任务最先进的方法产生性能竞争力,同时更加稳定,而不需要任何培训。我们的源代码和预先训练的型号可在线获取:https://razvanmarinescu.github.io/brgm/。
translated by 谷歌翻译
The primary aim of single-image super-resolution is to construct a high-resolution (HR) image from a corresponding low-resolution (LR) input. In previous approaches, which have generally been supervised, the training objective typically measures a pixel-wise average distance between the super-resolved (SR) and HR images. Optimizing such metrics often leads to blurring, especially in high variance (detailed) regions. We propose an alternative formulation of the super-resolution problem based on creating realistic SR images that downscale correctly. We present a novel super-resolution algorithm addressing this problem, PULSE (Photo Upsampling via Latent Space Exploration), which generates high-resolution, realistic images at resolutions previously unseen in the literature. It accomplishes this in an entirely self-supervised fashion and is not confined to a specific degradation operator used during training, unlike previous methods (which require training on databases of LR-HR image pairs for supervised learning). Instead of starting with the LR image and slowly adding detail, PULSE traverses the high-resolution natural image manifold, searching for images that downscale to the original LR image. This is formalized through the "downscaling loss," which guides exploration through the latent space of a generative model. By leveraging properties of high-dimensional Gaussians, we restrict the search space to guarantee that our outputs are realistic. PULSE thereby generates super-resolved images that both are realistic and downscale correctly. We show extensive experimental results demonstrating the efficacy of our approach in the domain of face super-resolution (also known as face hallucination). We also present a discussion of the limitations and biases of the method as currently implemented with an accompanying model card with relevant metrics. Our method outperforms state-of-the-art methods in perceptual quality at higher resolutions and scale factors than previously pos-sible.
translated by 谷歌翻译
随着深度学习(DL)的出现,超分辨率(SR)也已成为一个蓬勃发展的研究领域。然而,尽管结果有希望,但该领域仍然面临需要进一步研究的挑战,例如,允许灵活地采样,更有效的损失功能和更好的评估指标。我们根据最近的进步来回顾SR的域,并检查最新模型,例如扩散(DDPM)和基于变压器的SR模型。我们对SR中使用的当代策略进行了批判性讨论,并确定了有前途但未开发的研究方向。我们通过纳入该领域的最新发展,例如不确定性驱动的损失,小波网络,神经体系结构搜索,新颖的归一化方法和最新评估技术来补充先前的调查。我们还为整章中的模型和方法提供了几种可视化,以促进对该领域趋势的全球理解。最终,这篇综述旨在帮助研究人员推动DL应用于SR的界限。
translated by 谷歌翻译
These notes were compiled as lecture notes for a course developed and taught at the University of the Southern California. They should be accessible to a typical engineering graduate student with a strong background in Applied Mathematics. The main objective of these notes is to introduce a student who is familiar with concepts in linear algebra and partial differential equations to select topics in deep learning. These lecture notes exploit the strong connections between deep learning algorithms and the more conventional techniques of computational physics to achieve two goals. First, they use concepts from computational physics to develop an understanding of deep learning algorithms. Not surprisingly, many concepts in deep learning can be connected to similar concepts in computational physics, and one can utilize this connection to better understand these algorithms. Second, several novel deep learning algorithms can be used to solve challenging problems in computational physics. Thus, they offer someone who is interested in modeling a physical phenomena with a complementary set of tools.
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
压缩传感(CS)一直在加速磁共振成像(MRI)采集过程中的关键作用。随着人工智能的复苏,深神经网络和CS算法正在集成以重新定义快速MRI的领域。过去几年目睹了基于深度学习的CS技术的复杂性,多样性和表现的大量增长,这些技术致力于快速MRI。在该荟萃分析中,我们系统地审查了快速MRI的深度学习的CS技术,描述了关键模型设计,突出突破,并讨论了有希望的方向。我们还介绍了一个综合分析框架和分类系统,以评估深度学习在基于CS的加速度的MRI的关键作用。
translated by 谷歌翻译
现实的高光谱图像(HSI)超分辨率(SR)技术旨在从其低分辨率(LR)对应物中产生具有更高光谱和空间忠诚的高分辨率(HR)HSI。生成的对抗网络(GAN)已被证明是图像超分辨率的有效深入学习框架。然而,现有GaN的模型的优化过程经常存在模式崩溃问题,导致光谱间不变重建容量有限。这可能导致所生成的HSI上的光谱空间失真,尤其是具有大的升级因子。为了缓解模式崩溃的问题,这项工作提出了一种与潜在编码器(Le-GaN)耦合的新型GaN模型,其可以将产生的光谱空间特征从图像空间映射到潜在空间并产生耦合组件正规化生成的样本。基本上,我们将HSI视为嵌入在潜在空间中的高维歧管。因此,GaN模型的优化被转换为学习潜在空间中的高分辨率HSI样本的分布的问题,使得产生的超分辨率HSI的分布更接近其原始高分辨率对应物的那些。我们对超级分辨率的模型性能进行了实验评估及其在缓解模式崩溃中的能力。基于具有不同传感器(即Aviris和UHD-185)的两种实际HSI数据集进行了测试和验证,用于各种升高因素并增加噪声水平,并与最先进的超分辨率模型相比(即Hyconet,LTTR,Bagan,SR-GaN,Wgan)。
translated by 谷歌翻译
逆问题本质上是普遍存在的,几乎在科学和工程的几乎所有领域都出现,从地球物理学和气候科学到天体物理学和生物力学。解决反问题的核心挑战之一是解决他们的不良天性。贝叶斯推论提供了一种原则性的方法来克服这一方法,通过将逆问题提出为统计框架。但是,当推断具有大幅度的离散表示的字段(所谓的“维度的诅咒”)和/或仅以先前获取的解决方案的形式可用时。在这项工作中,我们提出了一种新的方法,可以使用深层生成模型进行有效,准确的贝叶斯反转。具体而言,我们证明了如何使用生成对抗网络(GAN)在贝叶斯更新中学到的近似分布,并在GAN的低维度潜在空间中重新解决所得的推断问题,从而有效地解决了大规模的解决方案。贝叶斯逆问题。我们的统计框架保留了潜在的物理学,并且被证明可以通过可靠的不确定性估计得出准确的结果,即使没有有关基础噪声模型的信息,这对于许多现有方法来说都是一个重大挑战。我们证明了提出方法对各种反问题的有效性,包括合成和实验观察到的数据。
translated by 谷歌翻译
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.
translated by 谷歌翻译