Article
Engineering, Electrical & Electronic
Adrian Vega Delgado, Matilde Sanchez-Fernandez, Luca Venturino, Antonia Tulino
Summary: This work explores super-resolving echoes from multiple prospective targets using a mmWave pulse radar. A novel signal model is derived with a structured steering vector and multi-dimensional frequency vector, recovering unknown frequency vectors and atoms using atomic norm and Vandermonde decomposition. Unique resolvability conditions in noiseless cases are discussed, along with a low-complexity formulation for recovery and numerical results for validation.
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING
(2021)
Article
Engineering, Mechanical
Zhao Li, Pedro Lee, Ross Murch
Summary: This paper proposes a method for estimating the super-resolved impulse response of a water pipeline system using compressive sensing, providing super-resolution results by reconstructing a sparse impulse response. This unique reconstruction can accurately distinguish closely spaced defects and accurately localize them.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2021)
Article
Engineering, Electrical & Electronic
Mohamed A. Suliman, Wei Dai
Summary: We study the problem of identifying the parameters of a linear system from its response to multiple unknown waveforms. By introducing constraints and developing a 2D super-resolution framework, we are able to fully characterize the system and recover all unknown parameters with high probability.
IEEE TRANSACTIONS ON SIGNAL PROCESSING
(2022)
Article
Engineering, Electrical & Electronic
Mohamed A. Suliman, Wei Dai
Summary: This paper introduces a new mathematical framework for denoising and parameter estimation in blind super-resolution. By solving a regularized least-squares atomic norm minimization problem, highly accurate estimation of noise-free signal can be obtained.
IEEE TRANSACTIONS ON SIGNAL PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Jianqi Ma, Shi Guo, Lei Zhang
Summary: This paper proposes a method to improve the resolution and visual quality of scene text images by embedding text recognition prior into the super-resolution model, which also boosts the performance of text recognition. Experimental results show that this method effectively improves the visual quality of scene text images and significantly enhances the text recognition accuracy.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Article
Engineering, Electrical & Electronic
Milad Javadzadeh Jirhandeh, Mohammad Hossein Kahaei
Summary: This paper proposes a super-resolution based method for coherent Direction Of Arrival (DOA) estimation of multiple wideband sources. By introducing an atomic norm problem and exploiting signal joint sparsity, a higher resolution and more robust DOA estimation method is achieved.
Article
Computer Science, Artificial Intelligence
Chenxi Ma, Weimin Tan, Bo Yan, Shili Zhou
Summary: This paper proposes an end-to-end approach for multi-degradations super-resolution (MDSR) that effectively extracts and embeds features using the degradation feature extraction module and the prior embedding module. The axis attention mechanism and the pixel attention mechanism are introduced to enhance the representation power of image features. Extensive experiments demonstrate the advantages of the proposed approach in solving different degradation problems.
Article
Geochemistry & Geophysics
Zhaori Gong, Nannan Wang, De Cheng, Xinrui Jiang, Jingwei Xin, Xi Yang, Xinbo Gao
Summary: In this study, a new method for hyperspectral image super-resolution reconstruction was proposed, which utilizes deep prior knowledge in a non-training approach and incorporates a special network input processing module for automatically adjusting the input structure. This method enhances the applicability and extendibility of hyperspectral image super-resolution reconstruction tasks.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Artificial Intelligence
Tao Lu, Yuanzhi Wang, Yanduo Zhang, Junjun Jiang, Zhongyuan Wang, Zixiang Xiong
Summary: This article proposes a novel pre-prior guided approach that extracts facial prior information from high-resolution face images and embeds them into low-resolution ones, resulting in high-frequency information-rich low-resolution face images and improved face reconstruction performance.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Jiaming Wang, Zhenfeng Shao, Xiao Huang, Tao Lu, Ruiqian Zhang, Jiayi Ma
Summary: This paper introduces an unsupervised learning framework called EIP, which can achieve the SR task without low/high resolution image pairs, by transferring texture and structured information from a reference image to an enhanced image prior using a recurrent updating strategy. Experimental results show that EIP outperforms state-of-the-art unsupervised SR methods both quantitatively and qualitatively.
Article
Computer Science, Artificial Intelligence
Chaoxiong Wu, Jiaojiao Li, Rui Song, Yunsong Li, Qian Du
Summary: Spectral super-resolution (SSR) is a challenging problem of recovering hyperspectral images (HSIs) from RGB counterparts. This article proposes a novel holistic prior-embedded relation network (HPRN) to address the ill-posed nature of SSR by integrating comprehensive priors. The HPRN framework consists of multiresidual relation blocks (MRBs) to utilize the low-frequency content prior of RGB images, semantic-driven spatial relation module (SSRM) for feature aggregation, and transformer-based channel relation module (TCRM) for robust mapping function. Experimental results demonstrate that the proposed HPRN achieves state-of-the-art performance in quantitative and qualitative SSR evaluation, and the effectiveness of the reconstructed spectra is verified through classification results on a remote sensing dataset.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Mengyang Shi, Yesheng Gao, Lin Chen, Xingzhao Liu
Summary: Image super-resolution is an effective technique for increasing image details, and we propose a neural network model called YSRNet that transforms a traditional optimization process into a learnable network. Combining conventional reconstruction methods and neural networks significantly improves the algorithm's performance.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Computer Science, Information Systems
Sujy Han, Tae Bok Lee, Yong Seok Heo
Summary: This paper introduces a noise-robust and stable framework based on deep image prior for single image super-resolution tasks. By utilizing generative adversarial networks and self-supervision loss for noise estimation, the proposed method outperforms existing approaches for noisy images.
Article
Mathematics, Applied
Qiuwei Li, Ashley Prater, Lixin Shen, Gongguo Tang
Summary: This work proposes a super-resolution framework for overcomplete tensor decomposition, where tensor decomposition is viewed as a problem of recovering a sum of Dirac measures on the sphere. By minimizing a continuous analog of the l(1) norm, the framework solves the problem and defines the tensor nuclear norm. Incoherence conditions of the tensor factors are derived to ensure unique optimal solution, and these conditions are satisfied with high probability by random tensor factors uniformly distributed on the sphere, implying global identifiability of random tensor factors.
INFORMATION AND INFERENCE-A JOURNAL OF THE IMA
(2022)
Article
Computer Science, Theory & Methods
Tao Zhang, Yongsheng Hu, Ran Lai
Summary: A gridless SR-STAP method is proposed in this study, which can accurately estimate clutter spectrum in the continuous angle-Doppler domain and achieve better performance compared to other methods.
MULTIDIMENSIONAL SYSTEMS AND SIGNAL PROCESSING
(2021)
Article
Engineering, Electrical & Electronic
Myung Cho, Kumar Vijay Mishra, Jian-Feng Cai, Weiyu Xu
IEEE SIGNAL PROCESSING LETTERS
(2015)
Article
Radiology, Nuclear Medicine & Medical Imaging
Myung Cho, Xiaodong Wu, Hossein Dadkhah, Jirong Yi, Ryan T. Flynn, Yusung Kim, Weiyu Xu
Article
Engineering, Electrical & Electronic
Myung Cho, Kumar Vijay Mishra, Weiyu Xu
EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING
(2018)
Article
Engineering, Electrical & Electronic
Myung Cho, Lifeng Lai, Weiyu Xu
Summary: This paper explores the convergence rate of distributed dual coordinate ascent for machine learning on a general tree-structured network. By analyzing the network effect and optimizing the algorithm considering communication delays, the study aims to maximize convergence speed. Numerical experiments demonstrate the algorithm's usability in tree networks where direct communication to a central node is not possible.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2021)
Article
Biochemical Research Methods
Kody A. Waldstein, Jirong Yi, Michael Myung Cho, Raghu Mudumbai, Xiaodong Wu, Steven M. Varga, Weiyu Xu
Summary: The rapid spread of SARS-CoV-2 has highlighted the need for innovative testing approaches for future pandemics. In this study, a novel sample pooling procedure based on compressed sensing theory is presented, which accurately identifies virally infected patients at high prevalence rates. The method reduces the number of tests required and provides quantification of individual sample viral load within a pool.
PLOS COMPUTATIONAL BIOLOGY
(2022)
Article
Mathematics, Applied
Jirong Yi, Soura Dasgupta, Jian-Feng Cai, Mathews Jacob, Jingchao Gao, Myung Cho, Weiyu Xu
Summary: This paper addresses the problem of recovering a superposition of R distinct complex exponential functions from compressed non-uniform time-domain samples. It is shown that the Hankel matrix recovery approach can achieve super-resolution in the presence of close frequencies. A new concept of orthonormal atomic norm minimization is proposed, which proves successful in cases where the original atoms are arbitrarily close. As a result of this research, a matrix-theoretic inequality of nuclear norm is provided.
INFORMATION AND INFERENCE-A JOURNAL OF THE IMA
(2023)
Proceedings Paper
Acoustics
Myung Cho, Lifeng Lai, Weiyu Xu
2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
(2019)
Proceedings Paper
Acoustics
Myung Cho, Yuejie Chi
2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
(2019)
Proceedings Paper
Computer Science, Information Systems
Weiyu Xu, Jirong Yi, Soura Dasgupta, Jian-Feng Cai, Mathews Jacob, Myung Cho
2018 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY (ISIT)
(2018)
Proceedings Paper
Acoustics
Myung Cho, Christos Thrampoulidis, Weiyu Xu, Babak Hassibi
2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
(2017)
Proceedings Paper
Acoustics
Myung Cho, Jian-Feng Cai, Suhui Liu, Yonina C. Eldar, Weiyu Xu
2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS
(2016)