PyTorchKR Papers

최신 논문

총 547편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2210.15242

Compressed-Sensing-Based 3D Localization with Distributed Passive Reconfigurable Intelligent Surfaces

In this paper, the programmable signal propagation paradigm, enabled by Reconfigurable Intelligent Surfaces (RISs), is exploited for high accuracy $3$-Dimensional (3D) user localization with a single multi-antenna base station. Capitalizing on the tunable reflection capability of passive RISs, we present a two-stage user localization method leveraging the multi-reflection wireless environment. In the first stage, we deploy an off-grid compressive sensing approach, which is based on the atomic norm minimization, for estimating the angles of arrival associated with each RIS, which is followed, in the second stage, by a maximum likelihood location estimation initialized with a least-squares line intersection technique. The presented numerical results showcase the high accuracy of the proposed 3D localization method, verifying our theoretical Cram\'er Rao lower bound analysis.

arXiv:2210.11483

Comparison between Hadamard and canonical bases for in-situ wavefront correction and the effect of ordering in compressive sensing

In this work we compare the Canonical and Hadamard bases for in-situ wavefront correction of a focused Gaussian beam using a spatial light modulator (SLM). The beam is perturbed with a transparent optical element (sparse) or a random scatterer (both prevent focusing at a single spot). The phase corrections are implemented with different basis sizes ($N=64, 256, 1024, 4096$) and the phase contribution of each basis element is measured with 3 step interferometry. The field is reconstructed from the complete $3N$ measurements and the correction is implemented by projecting the conjugate phase at the SLM. Our experiments show that in general, the Hadamard basis measurements yield better corrections because every element spans the relevant area of the SLM, reducing the noise in the interferograms. % In contrast, the canonical basis has the fundamental limitation that the area of the elements is proportional to $1/N$, and requires dimensions that are compatible with the spatial period of the grating. In the case of the random scatterer, we were only able to get reasonable corrections with the Hadamard basis and the intensity of the corrected spot increased monotonically with $N$, which is consistent with fast random changes in phase over small spatial scales. We also explore compressive sensing with the Hadamard basis and find that the minimum compression ratio needed to achieve corrections with similar quality to those that use the complete measurements depend on the basis ordering. The best results are reached in the case of the Hadamard-Walsh and cake cutting orderings. Surprisingly, in the case of the random scatterer we find that moderate compression ratios on the order of $10-20\%$ ($N=4096$) allow to recover focused spots, although as expected, the maximum intensities increase monotonically with the number of measurements due to the non sparsity of the signal.

arXiv:2210.09445

Hybrid mmWave MIMO Systems under Hardware Impairments and Beam Squint: Channel Model and Dictionary Learning-aided Configuration

Low overhead channel estimation based on compressive sensing (CS) has been widely investigated for hybrid wideband millimeter wave (mmWave) multiple-input multiple-output (MIMO) systems. The channel sparsifying dictionaries used in prior work are built from ideal array response vectors evaluated on discrete angles of arrival/departure. In addition, these dictionaries are assumed to be the same for all subcarriers, without considering the impacts of hardware impairments and beam squint. In this manuscript, we derive a general channel and signal model that explicitly incorporates the impacts of hardware impairments, practical pulse shaping functions, and beam squint, overcoming the limitations of mmWave MIMO channel and signal models commonly used in previous work. Then, we propose a dictionary learning (DL) algorithm to obtain the sparsifying dictionaries embedding hardware impairments, by considering the effect of beam squint without introducing it into the learning process. We also design a novel CS channel estimation algorithm under beam squint and hardware impairments, where the channel structures at different subcarriers are exploited to enable channel parameter estimation with low complexity and high accuracy. Numerical results demonstrate the effectiveness of the proposed DL and channel estimation strategy when applied to realistic mmWave channels.

arXiv:2210.08204

Compressive Sensing of ECG Signals using Plug-and-Play Regularization

Compressive Sensing (CS) has recently attracted attention for ECG data compression. In CS, an ECG signal is projected onto a small set of random vectors. Recovering the original signal from such compressed measurements remains a challenging problem. Traditional recovery methods are based on solving a regularized minimization problem, where a sparsity-promoting prior is used. In this paper, we propose an alternative iterative recovery algorithm based on the Plug-and-Play (PnP) method, which has recently become popular for imaging problems. In PnP, a powerful denoiser is used to implicitly perform regularization, instead of using hand-crafted regularizers; this has been found to be more successful than traditional methods. In this work, we use a PnP version of the Proximal Gradient Descent (PGD) algorithm for ECG recovery. To ensure mathematical convergence of the PnP algorithm, the signal denoiser in question needs to satisfy some technical conditions. We use a high-quality ECG signal denoiser fulfilling this condition by learning a Bayesian prior for small-sized signal patches. This guarantees that the proposed algorithm converges to a fixed point irrespective of the initialization. Importantly, through extensive experiments, we show that the reconstruction quality of the proposed method is superior to that of state-of-the-art methods.

arXiv:2209.11342

Fast Disparity Estimation from a Single Compressed Light Field Measurement

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.

arXiv:2209.01763

Uformer-ICS: A U-Shaped Transformer for Image Compressive Sensing Service

Many service computing applications require real-time dataset collection from multiple devices, necessitating efficient sampling techniques to reduce bandwidth and storage pressure. Compressive sensing (CS) has found wide-ranging applications in image acquisition and reconstruction. Recently, numerous deep-learning methods have been introduced for CS tasks. However, the accurate reconstruction of images from measurements remains a significant challenge, especially at low sampling rates. In this paper, we propose Uformer-ICS as a novel U-shaped transformer for image CS tasks by introducing inner characteristics of CS into transformer architecture. To utilize the uneven sparsity distribution of image blocks, we design an adaptive sampling architecture that allocates measurement resources based on the estimated block sparsity, allowing the compressed results to retain maximum information from the original image. Additionally, we introduce a multi-channel projection (MCP) module inspired by traditional CS optimization methods. By integrating the MCP module into the transformer blocks, we construct projection-based transformer blocks, and then form a symmetrical reconstruction model using these blocks and residual convolutional blocks. Therefore, our reconstruction model can simultaneously utilize the local features and long-range dependencies of image, and the prior projection knowledge of CS theory. Experimental results demonstrate its significantly better reconstruction performance than state-of-the-art deep learning-based CS methods.

arXiv:2208.10863

Contact-Free Multi-Target Tracking Using Distributed Massive MIMO-OFDM Communication System: Prototype and Analysis

Wireless-based human activity recognition has become an essential technology that enables contact-free human-machine and human-environment interactions. In this paper, we consider contact-free multi-target tracking (MTT) based on available communication systems. A radar-like prototype is built upon a sub-6 GHz distributed massive multiple-input and multiple-output (MIMO) orthogonal frequency-division multiplexing communication system. Specifically, the raw channel state information (CSI) is calibrated in the frequency and antenna domain before being used for tracking. Then the targeted CSIs reflected or scattered from the moving pedestrians are extracted. To evade the complex association problem of distributed massive MIMO-based MTT, we propose to use a complex Bayesian compressive sensing (CBCS) algorithm to estimate the targets' locations based on the extracted target-of-interest CSI signal directly. The estimated locations from CBCS are fed to a Gaussian mixture probability hypothesis density filter for tracking. A multi-pedestrian tracking experiment is conducted in a room with size of 6.5 m$\times$10 m to evaluate the performance of the proposed algorithm. According to experimental results, we achieve 75th and 95th percentile accuracy of 12.7 cm and 18.2 cm for single-person tracking and 28.9 cm and 45.7 cm for multi-person tracking, respectively. Furthermore, the proposed algorithm achieves the tracking purposes in real-time, which is promising for practical MTT use cases.

arXiv:2208.06670

Joint Localization and Information Transfer for Reconfigurable Intelligent Surface Aided Full-Duplex Systems

In this work, we investigate a reconfigurable intelligent surface (RIS) aided integrated sensing and communication scenario, where a base station (BS) communicates with multiple devices in a full-duplex mode, and senses the positions of these devices simultaneously. An RIS is assumed to be mounted on each device to enhance the reflected echoes. Meanwhile, the information of each device is passively transferred to the BS via reflection modulation. We aim to tackle the problem of joint localization and information retrieval at the BS. A grid based parametric model is constructed and the joint estimation problem is formulated as a compressive sensing problem. We propose a novel message-passing algorithm to solve the considered problem, and a progressive approximation method to reduce the computational complexity involved in the message passing. Moreover, an expectation-maximization (EM) algorithm is applied for tuning the grid parameters to mitigate the model mismatch problem. Finally, we analyze the efficacy of the proposed algorithm through the Bayesian Cram\'er-Rao bound. Numerical results demonstrate the feasibility of the proposed scheme and the superior performance of the proposed EM-based message-passing algorithm.

arXiv:2208.04515

Compressive Sensing Based Sparse MIMO Array Optimization for Wideband Near-Field Imaging

In the area of near-field millimeter-wave imaging, the generalized sparse array synthesis (SAS) method is in great demand. The traditional methods usually employ the greedy algorithms, which may have the convergence problem. This paper proposes a convex optimization model for the multiple-input multiple-output (MIMO) array design based on the compressive sensing (CS) approach. We generate a block shaped reference pattern, to be used as an optimizing target. The pattern occupies the entire imaging area of interest in order to involve the effect of each pixel into the optimization model. In MIMO scenarios, we can fix the transmit subarray and synthesize the receive subarray, and vice versa, or doing the synthesis sequentially. The problems associated with focusing, sidelobes suppression, and grating lobes suppression of the synthesized array are examined in details. Numerical and experimental results demonstrate that the synthesized sparse array can offer better image qualities than the sparse arrays with equally spaced or randomly spaced antennas with the same number of antenna elements.

arXiv:2208.03369공식 코드 · Papers with Code

A Spatially Separable Attention Mechanism for massive MIMO CSI Feedback

Channel State Information (CSI) Feedback plays a crucial role in achieving higher gains through beamforming. However, for a massive MIMO system, this feedback overhead is huge and grows linearly with the number of antennas. To reduce the feedback overhead several compressive sensing (CS) techniques were implemented in recent years but these techniques are often iterative and are computationally complex to realize in power-constrained user equipment (UE). Hence, a data-based deep learning approach took over in these recent years introducing a variety of neural networks for CSI compression. Specifically, transformer-based networks have been shown to achieve state-of-the-art performance. However, the multi-head attention operation, which is at the core of transformers, is computationally complex making transformers difficult to implement on a UE. In this work, we present a lightweight transformer named STNet which uses a spatially separable attention mechanism that is significantly less complex than the traditional full-attention. Equipped with this, STNet outperformed state-of-the-art models in some scenarios with approximately $1/10^{th}$ of the resources.

arXiv:2208.00422

Unitary Approximate Message Passing for Matrix Factorization

We consider matrix factorization (MF) with certain constraints, which finds wide applications in various areas. Leveraging variational inference (VI) and unitary approximate message passing (UAMP), we develop a Bayesian approach to MF with an efficient message passing implementation, called UAMPMF. With proper priors imposed on the factor matrices, UAMPMF can be used to solve many problems that can be formulated as MF, such as non negative matrix factorization, dictionary learning, compressive sensing with matrix uncertainty, robust principal component analysis, and sparse matrix factorization. Extensive numerical examples are provided to show that UAMPMF significantly outperforms state-of-the-art algorithms in terms of recovery accuracy, robustness and computational complexity.

arXiv:2207.14107

Fast Compressive Channel Estimation for MmWave MIMO Hybrid Beamforming Systems

Given the high degree of computational complexity of the channel estimation technique based on the conventional one-dimensional (1-D) compressive sensing (CS) framework employed in the hybrid beamforming architecture, this study proposes two low-complexity channel estimation strategies. One is two-stage CS, which exploits row-group sparsity to estimate angle-of-arrival (AoA) first and uses the conventional 1-D CS method to obtain angle-of-departure (AoD). The other is two-dimensional (2-D) CS, which utilizes a 2-D dictionary to reconstruct the 2-D sparse signal. To conduct a meaningful comparison of the three CS frameworks, i.e., 1-D, two-stage and 2-D CS, the orthogonal match pursuit (OMP) algorithm is employed as the basic algorithm and is expanded to two variants for the proposed frameworks. Analysis and simulations demonstrate that when the 1-D CS method is compared, two-stage CS has somewhat lower performance but significantly lower computational complexity, while 2-D CS is not only the same as 1-D CS in terms of performance but also slightly lower in computational complexity than two-stage CS.

arXiv:2207.14103

Low-complexity Sparse Array Synthesis Based on Off-grid Compressive Sensing

A novel sparse array synthesis method for non-uniform planar arrays is proposed, which belongs to compressive sensing (CS)-based systhesis. Particularly, we propose an off-grid refinement technique to simultaneously optimize the antenna element positions and excitations with a low complexity, in response to the antenna position optimization problem that is difficult for standard CS. More importantly, we take into account the minimum inter-element spacing constraint for ensuring the physically realizable solution. Specifically, the off-grid Orthogonal Match Pursuit (OMP) algorithm is first proposed with low complexity and then off-grid Look Ahead Orthogonal Match Pursuit (LAOMP) is designed with better synthesis performance but higher complexity. In addition, simulation results have shown the proposed schemes have more advantages in computational complexity and synthesis performances compared with the related method.

arXiv:2207.14182

Channel Estimation for Reconfigurable Intelligent Surface-Assisted Cell-Free Communications

Recent research has focused on reconfigurable intelligent surface (RIS)-assisted cell-free systems with the goal of enhancing coverage and lowering the cost of cell-free networks. However, current research makes the assumption that the perfect channel state information is known. Channel acquisition is, certainly, a difficulty in this case. This work is aimed at investigating RIS-assisted cell-free channel estimation. Toward this end, two unique characteristics are pointed out: 1) For all users, a common channel exists between the base station (BS) and the RIS; and 2) For all BSs, a common channel exists between the RIS and the user. Based on these two characteristics, cascaded and two-timescale channel estimation concerns are studied. Subsequently, two solutions for tackling with the two issues are presented respectively: a three-dimensional multiple measurement vector (3D-MMV)-based compressive sensing technique and a multi-BS cooperative pilot-reduced methodology. Finally, simulations illustrate the effectiveness of the schemes we have presented.

arXiv:2207.13560공식 코드 · Papers with Code

D3C2-Net: Dual-Domain Deep Convolutional Coding Network for Compressive Sensing

By mapping iterative optimization algorithms into neural networks (NNs), deep unfolding networks (DUNs) exhibit well-defined and interpretable structures and achieve remarkable success in the field of compressive sensing (CS). However, most existing DUNs solely rely on the image-domain unfolding, which restricts the information transmission capacity and reconstruction flexibility, leading to their loss of image details and unsatisfactory performance. To overcome these limitations, this paper develops a dual-domain optimization framework that combines the priors of (1) image- and (2) convolutional-coding-domains and offers generality to CS and other inverse imaging tasks. By converting this optimization framework into deep NN structures, we present a Dual-Domain Deep Convolutional Coding Network (D3C2-Net), which enjoys the ability to efficiently transmit high-capacity self-adaptive convolutional features across all its unfolded stages. Our theoretical analyses and experiments on simulated and real captured data, covering 2D and 3D natural, medical, and scientific signals, demonstrate the effectiveness, practicality, superior performance, and generalization ability of our method over other competing approaches and its significant potential in achieving a balance among accuracy, complexity, and interpretability. Code is available at https://github.com/lwq20020127/D3C2-Net.

arXiv:2207.09594

ICRICS: Iterative Compensation Recovery for Image Compressive Sensing

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.

arXiv:2207.07301

Robust Deep Compressive Sensing with Recurrent-Residual Structural Constraints

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.

arXiv:2207.06746

Single-Pixel Image Reconstruction Based on Block Compressive Sensing and Deep Learning

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.

arXiv:2206.14373

Theoretical Perspectives on Deep Learning Methods in Inverse Problems

In recent years, there have been significant advances in the use of deep learning methods in inverse problems such as denoising, compressive sensing, inpainting, and super-resolution. While this line of works has predominantly been driven by practical algorithms and experiments, it has also given rise to a variety of intriguing theoretical problems. In this paper, we survey some of the prominent theoretical developments in this line of works, focusing in particular on generative priors, untrained neural network priors, and unfolding algorithms. In addition to summarizing existing results in these topics, we highlight several ongoing challenges and open problems.

arXiv:2206.14199

Hyperspectral image reconstruction for spectral camera based on ghost imaging via sparsity constraints using V-DUnet

Spectral camera based on ghost imaging via sparsity constraints (GISC spectral camera) obtains three-dimensional (3D) hyperspectral information with two-dimensional (2D) compressive measurements in a single shot, which has attracted much attention in recent years. However, its imaging quality and real-time performance of reconstruction still need to be further improved. Recently, deep learning has shown great potential in improving the reconstruction quality and reconstruction speed for computational imaging. When applying deep learning into GISC spectral camera, there are several challenges need to be solved: 1) how to deal with the large amount of 3D hyperspectral data, 2) how to reduce the influence caused by the uncertainty of the random reference measurements, 3) how to improve the reconstructed image quality as far as possible. In this paper, we present an end-to-end V-DUnet for the reconstruction of 3D hyperspectral data in GISC spectral camera. To reduce the influence caused by the uncertainty of the measurement matrix and enhance the reconstructed image quality, both differential ghost imaging results and the detected measurements are sent into the network's inputs. Compared with compressive sensing algorithm, such as PICHCS and TwIST, it not only significantly improves the imaging quality with high noise immunity, but also speeds up the reconstruction time by more than two orders of magnitude.