For solving linear inverse problems, particularly of the type that appear in tomographic imaging and compressive sensing, this paper develops two new approaches. The first approach is an iterative algorithm that minimizers a regularized least squares objective function where the regularization is based on a compound Gaussian prior distribution. The Compound Gaussian prior subsumes many of the commonly used priors in image reconstruction, including those of sparsity-based approaches. The developed iterative algorithm gives rise to the paper's second new approach, which is a deep neural network that corresponds to an "unrolling" or "unfolding" of the iterative algorithm. Unrolled deep neural networks have interpretable layers and outperform standard deep learning methods. This paper includes a detailed computational theory that provides insight into the construction and performance of both algorithms. The conclusion is that both algorithms outperform other state-of-the-art approaches to tomographic image formation and compressive sensing, especially in the difficult regime of low training.
为了解决线性逆问题,特别是出现在磁共振成像和压缩感知中的问题,本文开发了两种新的算法。第一种方法是迭代算法,其最小化的目标是 regularized 最小二乘法 objective function,其中Regularization是基于组合高斯先验分布的。组合高斯先验分布将许多在图像重建中常用的先验包括在内,包括基于密度的先验。开发迭代算法导致本文提出的第二种新算法,这是一种深度神经网络,与迭代算法的“展开”或“展开”对应。展开的深度神经网络具有可解释的层,并比标准深度学习方法表现更好。本文包括详细的计算理论,提供了对两个算法构造和性能的理解。结论是,两个算法在磁共振成像和压缩感知中的表现优于其他先进的方法,特别是在低训练状态下。
https://arxiv.org/abs/2305.11120
The use of deep unfolding networks in compressive sensing (CS) has seen wide success as they provide both simplicity and interpretability. However, since most deep unfolding networks are iterative, this incurs significant redundancies in the network. In this work, we propose a novel recursion-based framework to enhance the efficiency of deep unfolding models. First, recursions are used to effectively eliminate the redundancies in deep unfolding networks. Secondly, we randomize the number of recursions during training to decrease the overall training time. Finally, to effectively utilize the power of recursions, we introduce a learnable unit to modulate the features of the model based on both the total number of iterations and the current iteration index. To evaluate the proposed framework, we apply it to both ISTA-Net+ and COAST. Extensive testing shows that our proposed framework allows the network to cut down as much as 75% of its learnable parameters while mostly maintaining its performance, and at the same time, it cuts around 21% and 42% from the training time for ISTA-Net+ and COAST respectively. Moreover, when presented with a limited training dataset, the recursive models match or even outperform their respective non-recursive baseline. Codes and pretrained models are available at this https URL .
深度展开网络在压缩感知(CS)中广泛应用,因为它们既简单又易于解释。然而,由于大多数深度展开网络是迭代的,因此在网络中造成了巨大的冗余。在本研究中,我们提出了一种基于递归的新框架,以增强深度展开模型的效率。我们首先利用递归有效地消除深度展开网络中的冗余。其次,我们在训练期间随机化递归次数,以减少整个训练时间。最后,为了有效地利用递归的力量,我们引入一个可学习单元,根据迭代次数的总数量和当前迭代指数来调节模型的特征。为了评估所提出的框架,我们将其应用于ISTA-Net+和COAST。广泛的测试表明,我们提出的框架可以使网络最大限度地减少其可学习参数中的冗余,而大部分时间仍然保持其表现,同时,它分别减少了ISTA-Net+和COAST的训练时间中的约21%和42%。此外,当面对有限的训练数据时,递归模型几乎与或甚至超越了其非递归基线。代码和预训练模型可在本网站上https://url.com获得。
https://arxiv.org/abs/2305.05505
Deep learning has been applied to compressive sensing (CS) of images successfully in recent years. However, existing network-based methods are often trained as the black box, in which the lack of prior knowledge is often the bottleneck for further performance improvement. To overcome this drawback, this paper proposes a novel CS method using non-local prior which combines the interpretability of the traditional optimization methods with the speed of network-based methods, called NL-CS Net. We unroll each phase from iteration of the augmented Lagrangian method solving non-local and sparse regularized optimization problem by a network. NL-CS Net is composed of the up-sampling module and the recovery module. In the up-sampling module, we use learnable up-sampling matrix instead of a predefined one. In the recovery module, patch-wise non-local network is employed to capture long-range feature correspondences. Important parameters involved (e.g. sampling matrix, nonlinear transforms, shrinkage thresholds, step size, $etc.$) are learned end-to-end, rather than hand-crafted. Furthermore, to facilitate practical implementation, orthogonal and binary constraints on the sampling matrix are simultaneously adopted. Extensive experiments on natural images and magnetic resonance imaging (MRI) demonstrate that the proposed method outperforms the state-of-the-art methods while maintaining great interpretability and speed.
深度学习近年来成功地应用于图像压缩感知(CS)中。然而,现有的网络方法往往被训练为黑盒,缺乏先前知识往往成为进一步性能改进的瓶颈。为了克服这一缺点,本文提出了一种使用非局部先前的新型CS方法,该方法将传统的优化方法的解释性与网络方法的速度相结合,称为NL-CSNet。我们从扩展拉格朗日方法的迭代中展开每个阶段,以解决非局部和稀疏 Regularized 优化问题,通过网络实现。NL-CSNet由采样模块和恢复模块组成。在采样模块中,我们使用可学习采样矩阵而不是预先定义的矩阵。在恢复模块中,采用点 wise的非局部网络来捕捉长距离特征对应关系。参与重要参数(例如采样矩阵、非线性变换、收缩阈值、步长大小等)的学习是端到端学习的,而不是手工构建的。此外,为了促进实际实现,同时采用Orthogonal 和二进制采样矩阵约束。对自然图像和磁共振成像(MRI)进行了广泛的实验,证明了该方法在保持极大的解释性和速度优势的同时,击败了最先进的方法。
https://arxiv.org/abs/2305.03899
By integrating certain optimization solvers with deep neural networks, deep unfolding network (DUN) with good interpretability and high performance has attracted growing attention in compressive sensing (CS). However, existing DUNs often improve the visual quality at the price of a large number of parameters and have the problem of feature information loss during iteration. In this paper, we propose an Optimization-inspired Cross-attention Transformer (OCT) module as an iterative process, leading to a lightweight OCT-based Unfolding Framework (OCTUF) for image CS. Specifically, we design a novel Dual Cross Attention (Dual-CA) sub-module, which consists of an Inertia-Supplied Cross Attention (ISCA) block and a Projection-Guided Cross Attention (PGCA) block. ISCA block introduces multi-channel inertia forces and increases the memory effect by a cross attention mechanism between adjacent iterations. And, PGCA block achieves an enhanced information interaction, which introduces the inertia force into the gradient descent step through a cross attention block. Extensive CS experiments manifest that our OCTUF achieves superior performance compared to state-of-the-art methods while training lower complexity. Codes are available at this https URL.
通过将某些优化求解器和深度神经网络集成起来,具有良好解释性和高性能的深度展开网络(DUN)在压缩感知(CS)中越来越受到关注。然而,现有的DUN往往通过大量参数来提高视觉质量,并且在迭代过程中会出现特征信息丢失的问题。在本文中,我们提出一种基于优化的交叉注意力Transformer(OCT)模块作为迭代过程,从而生成轻量级的基于OCT的图像展开框架(OCTUF)。具体来说,我们设计了一个独特的双重交叉注意力(Dual-CA)子模块,其中包含一个惯性提供交叉注意力(ISCA)块和一个投影引导交叉注意力(PGCA)块。ISCA块引入了多通道惯性力,并通过相邻迭代中的交叉注意力机制增加记忆效应。PGCA块实现了增强的信息交互,通过交叉注意力块将惯性力引入梯度下降步骤。广泛的CS实验表明,我们的OCTUF在训练复杂性较低的情况下比现有方法表现出更好的性能。代码可在该httpsURL上获取。
https://arxiv.org/abs/2304.13986
Deep network-based image and video Compressive Sensing(CS) has attracted increasing attentions in recent years. However, in the existing deep network-based CS methods, a simple stacked convolutional network is usually adopted, which not only weakens the perception of rich contextual prior knowledge, but also limits the exploration of the correlations between temporal video frames. In this paper, we propose a novel Hierarchical InTeractive Video CS Reconstruction Network(HIT-VCSNet), which can cooperatively exploit the deep priors in both spatial and temporal domains to improve the reconstruction quality. Specifically, in the spatial domain, a novel hierarchical structure is designed, which can hierarchically extract deep features from keyframes and non-keyframes. In the temporal domain, a novel hierarchical interaction mechanism is proposed, which can cooperatively learn the correlations among different frames in the multiscale space. Extensive experiments manifest that the proposed HIT-VCSNet outperforms the existing state-of-the-art video and image CS methods in a large margin.
深度学习图像和视频压缩感知(CS)近年来日益受到关注。然而,在现有的深度学习CS方法中,通常采用简单的叠加卷积神经网络,这不仅削弱了丰富的上下文先验知识的感受度,而且也限制了对时间帧之间相关性的探索。在本文中,我们提出了一种新的Hierarchical InTeractive Video CS Reconstruction Network(HIT-VCSNet),它可以合作利用空间和时间域中的深层先验知识,以提高重建质量。具体来说,在空间域中,我们设计了一种 novel Hierarchical 结构,可以从关键帧和非关键帧中Hierarchically 提取深层特征。在时间域中,我们提出了一种 novel Hierarchical 交互机制,可以在多尺度空间中合作学习不同帧之间的相关性。广泛的实验表明,提出的HIT-VCSNet在显著优于现有的先进的视频和图像CS方法。
https://arxiv.org/abs/2304.07473
Model-based deep learning methods that combine imaging physics with learned regularization priors have been emerging as powerful tools for parallel MRI acceleration. The main focus of this paper is to determine the utility of the monotone operator learning (MOL) framework in the parallel MRI setting. The MOL algorithm alternates between a gradient descent step using a monotone convolutional neural network (CNN) and a conjugate gradient algorithm to encourage data consistency. The benefits of this approach include similar guarantees as compressive sensing algorithms including uniqueness, convergence, and stability, while being significantly more memory efficient than unrolled methods. We validate the proposed scheme by comparing it with different unrolled algorithms in the context of accelerated parallel MRI for static and dynamic settings.
基于模型的深度学习方法,将图像物理学与学习后的正则化预处理相结合,正在成为并行MRI加速的强大工具。本文的主要焦点是确定Monotone Operator Learning (MOL)框架在并行MRI设置中的实用性。MOL算法在采用Monotone卷积神经网络(CNN)和Conjugate Gradient算法的梯度下降步骤之间交替进行,以鼓励数据一致性。这种方法的好处包括与压缩感知算法类似的保证,包括独特性、收敛和稳定性,而比展开方法更有效地利用了内存。我们验证了所提出的 scheme 的方法,并将其与不同的展开算法在加速静态和动态MRI设置中的并行加速比较。
https://arxiv.org/abs/2304.01351
Deep networks can be trained to map images into a low-dimensional latent space. In many cases, different images in a collection are articulated versions of one another; for example, same object with different lighting, background, or pose. Furthermore, in many cases, parts of images can be corrupted by noise or missing entries. In this paper, our goal is to recover images without access to the ground-truth (clean) images using the articulations as structural prior of the data. Such recovery problems fall under the domain of compressive sensing. We propose to learn autoencoder with tensor ring factorization on the the embedding space to impose structural constraints on the data. In particular, we use a tensor ring structure in the bottleneck layer of the autoencoder that utilizes the soft labels of the structured dataset. We empirically demonstrate the effectiveness of the proposed approach for inpainting and denoising applications. The resulting method achieves better reconstruction quality compared to other generative prior-based self-supervised recovery approaches for compressive sensing.
深度网络可以被训练将图像映射到低维度的潜在空间。在许多情况下,一组图像是相互联系的版本;例如,相同的物体以不同的照明、背景或姿态呈现。此外,在许多情况下,图像的部分可以受到噪声或缺失值的影响。在本文中,我们的的目标是使用连接作为数据的结构先验来恢复图像,而连接则作为数据的结构约束。这种恢复问题属于压缩感知技术的范围。我们提议学习使用 Tensor环乘法将嵌入空间中的 Tensor环表示作为编码器的结构先验,并施加数据的结构约束。特别,我们将在编码器的瓶颈层中使用 Tensor环结构,利用结构数据集的软标签。我们经验证了该方法在填充和去噪应用中的的有效性。结果方法相对于其他基于生成先验的自监督恢复方法来说,实现了更好的重建质量。
https://arxiv.org/abs/2303.06235
We study a deep linear network endowed with a structure. It takes the form of a matrix $X$ obtained by multiplying $K$ matrices (called factors and corresponding to the action of the layers). The action of each layer (i.e. a factor) is obtained by applying a fixed linear operator to a vector of parameters satisfying a constraint. The number of layers is not limited. Assuming that $X$ is given and factors have been estimated, the error between the product of the estimated factors and $X$ (i.e. the reconstruction error) is either the statistical or the empirical risk. In this paper, we provide necessary and sufficient conditions on the network topology under which a stability property holds. The stability property requires that the error on the parameters defining the factors (i.e. the stability of the recovered parameters) scales linearly with the reconstruction error (i.e. the risk). Therefore, under these conditions on the network topology, any successful learning task leads to stably defined features and therefore interpretable layers/network.In order to do so, we first evaluate how the Segre embedding and its inverse distort distances. Then, we show that any deep structured linear network can be cast as a generic multilinear problem (that uses the Segre embedding). This is the {\em tensorial lifting}. Using the tensorial lifting, we provide necessary and sufficient conditions for the identifiability of the factors (up to a scale rearrangement). We finally provide the necessary and sufficient condition called \NSPlong~(because of the analogy with the usual Null Space Property in the compressed sensing framework) which guarantees that the stability property holds. We illustrate the theory with a practical example where the deep structured linear network is a convolutional linear network. As expected, the conditions are rather strong but not empty. A simple test on the network topology can be implemented to test if the condition holds.
我们研究了一个具有结构的深度学习线性网络。它的形式是 $K$ 个矩阵的乘积得到的矩阵 $X$,即称为 factors 并对应每个层的动作。每个层的动作(即一个 factors)是通过应用一个固定的线性操作对满足约束的参数向量进行计算得到的。层的数量不受限制。假设 $X$ 已经给定,并已经估计了 factors,则估计的 factors 与 $X$ 的乘积之差(即重建误差)可能是统计风险或经验风险。在本文中,我们提供了在网络拓扑下保持稳定性的必要条件和充分条件。稳定性性质要求定义 factors 的参数误差(即恢复参数的稳定性)以线性方式与重建误差(即风险)成正比。因此,在这些网络拓扑下,任何成功的学习任务都会导致稳定定义的特征,因此可解释的层/网络。为了这样做,我们首先评估了史格雷嵌入和它的逆对距离的影响。然后,我们表明,任何具有深刻结构深度学习线性网络都可以转换为一个通用多线性问题(使用史格雷嵌入)。这就是 Tensorial lifting。使用 Tensorial lifting,我们提供了 factors 的可确定性的必要条件和充分条件(到规模重构)。最后,我们提供了称为 NSPlong~(因为与压缩感知框架中的常见 null 空间 property 的类比)的必要和充分条件,以确保稳定性性质成立。我们使用实际示例来阐明理论,其中深刻的结构深度学习线性网络是一个卷积线性网络。正如预期的那样,条件相当强,但不是空的。可以通过网络拓扑的简单测试来测试条件是否成立。
https://arxiv.org/abs/1703.08044
Deep unfolding networks (DUNs) have proven to be a viable approach to compressive sensing (CS). In this work, we propose a DUN called low-rank CS network (LR-CSNet) for natural image CS. Real-world image patches are often well-represented by low-rank approximations. LR-CSNet exploits this property by adding a low-rank prior to the CS optimization task. We derive a corresponding iterative optimization procedure using variable splitting, which is then translated to a new DUN architecture. The architecture uses low-rank generation modules (LRGMs), which learn low-rank matrix factorizations, as well as gradient descent and proximal mappings (GDPMs), which are proposed to extract high-frequency features to refine image details. In addition, the deep features generated at each reconstruction stage in the DUN are transferred between stages to boost the performance. Our extensive experiments on three widely considered datasets demonstrate the promising performance of LR-CSNet compared to state-of-the-art methods in natural image CS.
https://arxiv.org/abs/2212.09088
Deep learning (DL)-based tomographic SAR imaging algorithms are gradually being studied. Typically, they use an unfolding network to mimic the iterative calculation of the classical compressive sensing (CS)-based methods and process each range-azimuth unit individually. However, only one-dimensional features are effectively utilized in this way. The correlation between adjacent resolution units is ignored directly. To address that, we propose a new model-data-driven network to achieve tomoSAR imaging based on multi-dimensional features. Guided by the deep unfolding methodology, a two-dimensional deep unfolding imaging network is constructed. On the basis of it, we add two 2D processing modules, both convolutional encoder-decoder structures, to enhance multi-dimensional features of the imaging scene effectively. Meanwhile, to train the proposed multifeature-based imaging network, we construct a tomoSAR simulation dataset consisting entirely of simulation data of buildings. Experiments verify the effectiveness of the model. Compared with the conventional CS-based FISTA method and DL-based gamma-Net method, the result of our proposed method has better performance on completeness while having decent imaging accuracy.
https://arxiv.org/abs/2211.15002
Most Deep Learning (DL) based Compressed Sensing (DCS) algorithms adopt a single neural network for signal reconstruction, and fail to jointly consider the influences of the sampling operation for reconstruction. In this paper, we propose unified framework, which jointly considers the sampling and reconstruction process for image compressive sensing based on well-designed cascade neural networks. Two sub-networks, which are the sampling sub-network and the reconstruction sub-network, are included in the proposed framework. In the sampling sub-network, an adaptive full connected layer instead of the traditional random matrix is used to mimic the sampling operator. In the reconstruction sub-network, a cascade network combining stacked denoising autoencoder (SDA) and convolutional neural network (CNN) is designed to reconstruct signals. The SDA is used to solve the signal mapping problem and the signals are initially reconstructed. Furthermore, CNN is used to fully recover the structure and texture features of the image to obtain better reconstruction performance. Extensive experiments show that this framework outperforms many other state-of-the-art methods, especially at low sampling rates.
https://arxiv.org/abs/2211.05963
The abundant spatial and angular information from light fields has allowed the development of multiple disparity estimation approaches. However, the acquisition of light fields requires high storage and processing cost, limiting the use of this technology in practical applications. To overcome these drawbacks, the compressive sensing (CS) theory has allowed the development of optical architectures to acquire a single coded light field measurement. This measurement is decoded using an optimization algorithm or deep neural network that requires high computational costs. The traditional approach for disparity estimation from compressed light fields requires first recovering the entire light field and then a post-processing step, thus requiring long times. In contrast, this work proposes a fast disparity estimation from a single compressed measurement by omitting the recovery step required in traditional approaches. Specifically, we propose to jointly optimize an optical architecture for acquiring a single coded light field snapshot and a convolutional neural network (CNN) for estimating the disparity maps. Experimentally, the proposed method estimates disparity maps comparable with those obtained from light fields reconstructed using deep learning approaches. Furthermore, the proposed method is 20 times faster in training and inference than the best method that estimates the disparity from reconstructed light fields.
https://arxiv.org/abs/2209.11342
Recently, several studies have applied deep convolutional neural networks (CNNs) in image compressive sensing (CS) tasks to improve reconstruction quality. However, convolutional layers generally have a small receptive field; therefore, capturing long-range pixel correlations using CNNs is challenging, which limits their reconstruction performance in image CS tasks. Considering this limitation, we propose a U-shaped transformer for image CS tasks, called the Uformer-ICS. We develop a projection-based transformer block by integrating the prior projection knowledge of CS into the original transformer blocks, and then build a symmetrical reconstruction model using the projection-based transformer blocks and residual convolutional blocks. Compared with previous CNN-based CS methods that can only exploit local image features, the proposed reconstruction model can simultaneously utilize the local features and long-range dependencies of an image, and the prior projection knowledge of the CS theory. Additionally, we design an adaptive sampling model that can adaptively sample image blocks based on block sparsity, which can ensure that the compressed results retain the maximum possible information of the original image under a fixed sampling ratio. The proposed Uformer-ICS is an end-to-end framework that simultaneously learns the sampling and reconstruction processes. Experimental results demonstrate that it achieves significantly better reconstruction performance than existing state-of-the-art deep learning-based CS methods.
https://arxiv.org/abs/2209.01763
Mapping optimization algorithms into neural networks, deep unfolding networks (DUNs) have achieved impressive success in compressive sensing (CS). From the perspective of optimization, DUNs inherit a well-defined and interpretable structure from iterative steps. However, from the viewpoint of neural network design, most existing DUNs are inherently established based on traditional image-domain unfolding, which takes one-channel images as inputs and outputs between adjacent stages, resulting in insufficient information transmission capability and inevitable loss of the image details. In this paper, to break the above bottleneck, we first propose a generalized dual-domain optimization framework, which is general for inverse imaging and integrates the merits of both (1) image-domain and (2) convolutional-coding-domain priors to constrain the feasible region in the solution space. By unfolding the proposed framework into deep neural networks, we further design a novel Dual-Domain Deep Convolutional Coding Network (D3C2-Net) for CS imaging with the capability of transmitting high-throughput feature-level image representation through all the unfolded stages. Experiments on natural and MR images demonstrate that our D3C2-Net achieves higher performance and better accuracy-complexity trade-offs than other state-of-the-arts.
https://arxiv.org/abs/2207.13560
Closed-loop architecture is widely utilized in automatic control systems and attain distinguished performance. However, classical compressive sensing systems employ open-loop architecture with separated sampling and reconstruction units. Therefore, a method of iterative compensation recovery for image compressive sensing (ICRICS) is proposed by introducing closed-loop framework into traditional compresses sensing systems. The proposed method depends on any existing approaches and upgrades their reconstruction performance by adding negative feedback structure. Theory analysis on negative feedback of compressive sensing systems is performed. An approximate mathematical proof of the effectiveness of the proposed method is also provided. Simulation experiments on more than 3 image datasets show that the proposed method is superior to 10 competition approaches in reconstruction performance. The maximum increment of average peak signal-to-noise ratio is 4.36 dB and the maximum increment of average structural similarity is 0.034 on one dataset. The proposed method based on negative feedback mechanism can efficiently correct the recovery error in the existing systems of image compressive sensing.
https://arxiv.org/abs/2207.09594
Existing deep compressive sensing (CS) methods either ignore adaptive online optimization or depend on costly iterative optimizer during reconstruction. This work explores a novel image CS framework with recurrent-residual structural constraint, termed as R$^2$CS-NET. The R$^2$CS-NET first progressively optimizes the acquired samplings through a novel recurrent neural network. The cascaded residual convolutional network then fully reconstructs the image from optimized latent representation. As the first deep CS framework efficiently bridging adaptive online optimization, the R$^2$CS-NET integrates the robustness of online optimization with the efficiency and nonlinear capacity of deep learning methods. Signal correlation has been addressed through the network architecture. The adaptive sensing nature further makes it an ideal candidate for color image CS via leveraging channel correlation. Numerical experiments verify the proposed recurrent latent optimization design not only fulfills the adaptation motivation, but also outperforms classic long short-term memory (LSTM) architecture in the same scenario. The overall framework demonstrates hardware implementation feasibility, with leading robustness and generalization capability among existing deep CS benchmarks.
https://arxiv.org/abs/2207.07301
Single-pixel imaging (SPI) is a novel imaging technique whose working principle is based on the compressive sensing (CS) theory. In SPI, data is obtained through a series of compressive measurements and the corresponding image is reconstructed. Typically, the reconstruction algorithm such as basis pursuit relies on the sparsity assumption in images. However, recent advances in deep learning have found its uses in reconstructing CS images. Despite showing a promising result in simulations, it is often unclear how such an algorithm can be implemented in an actual SPI setup. In this paper, we demonstrate the use of deep learning on the reconstruction of SPI images in conjunction with block compressive sensing (BCS). We also proposed a novel reconstruction model based on convolutional neural networks that outperforms other competitive CS reconstruction algorithms. Besides, by incorporating BCS in our deep learning model, we were able to reconstruct images of any size above a certain smallest image size. In addition, we show that our model is capable of reconstructing images obtained from an SPI setup while being priorly trained on natural images, which can be vastly different from the SPI images. This opens up opportunity for the feasibility of pretrained deep learning models for CS reconstructions of images from various domain areas.
https://arxiv.org/abs/2207.06746
Coded aperture snapshot spectral imaging (CASSI) is a technique used to reconstruct three-dimensional hyperspectral images (HSIs) from one or several two-dimensional projection measurements. However, fewer projection measurements or more spectral channels leads to a severly ill-posed problem, in which case regularization methods have to be applied. In order to significantly improve the accuracy of reconstruction, this paper proposes a fast alternating minimization algorithm based on the sparsity and deep image priors (Fama-SDIP) of natural images. By integrating deep image prior (DIP) into the principle of compressive sensing (CS) reconstruction, the proposed algorithm can achieve state-of-the-art results without any training dataset. Extensive experiments show that Fama-SDIP method significantly outperforms prevailing leading methods on simulation and real HSI datasets.
https://arxiv.org/abs/2206.05647
We introduce a monotone deep equilibrium learning framework for large-scale inverse problems in imaging. The proposed algorithm relies on forward-backward splitting, where each iteration consists of a gradient descent involving the score function and a conjugate gradient algorithm to encourage data consistency. The score function is modeled as a monotone convolutional neural network. The use of a monotone operator offers several benefits, including guaranteed convergence, uniqueness of fixed point, and robustness to input perturbations, similar to the use of convex priors in compressive sensing. In addition, the proposed formulation is significantly more memory-efficient than unrolled methods, which allows us to apply it to 3D problems that current unrolled algorithms cannot handle. Experiments show that the proposed scheme can offer improved performance in 3D settings while being stable in the presence of input perturbations.
https://arxiv.org/abs/2206.04797
The usually reported pixel resolution of single pixel imaging (SPI) varies between $32 \times 32$ and $256 \times 256$ pixels falling far below imaging standards with classical methods. Low resolution results from the trade-off between the acceptable compression ratio, the limited DMD modulation frequency, and reasonable reconstruction time, and has not improved significantly during the decade of intensive research on SPI. In this paper we show that image measurement at the full resolution of the DMD, which lasts only a fraction of a second, is possible for sparse images or in a situation when the field of view is limited but is a priori unknown. We propose the sampling and reconstruction strategies that enable us to reconstruct sparse images at the resolution of $1024 \times 768$ within the time of $0.3~$s. Non-sparse images are reconstructed with less details. The compression ratio is on the order of $0.4 \%$ which corresponds to an acquisition frequency of $7~$Hz. Sampling is differential, binary, and non-adaptive, and includes information on multiple partitioning of the image which later allows us to determine the actual field of view. Reconstruction is based on the differential Fourier domain regularized inversion (D-FDRI). The proposed SPI framework is an alternative to both adaptive SPI, which is challenging to implement in real time, and to classical compressive sensing image recovery methods, which are very slow at high resolutions.
https://arxiv.org/abs/2206.02510