Compressive Sensing via Nonlocal Low-Rank Regularization

By Weisheng Dong, Guangming Shi, Xin Li, Yi Ma, Feng Huang. IEEE Transactions on Image Processing, 2014

578 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computational Mechanics

View Paper: https://www.semanticscholar.org/paper/359d361e3edf138a8588a6a276df30aa129bab3f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computational Mechanics

Citations in the corpus

TensoRF: Tensorial Radiance Fields (2022, methodology): “In general, low-rank regularization is crucial in addressing many reconstruction problems, like matrix completion [1], compressive sensing [2], denoising [4]; tensor decomposition has also been widely used in tensor completion [5, 3], which is similar to our task.”
Weighted Nuclear Norm Minimization and Its Applications to Low Level Vision (2016, background): “Recently, (Dong et al. 2014) utilized nonconvex logdet (X) as a surrogate of the rank function and achieved state-of-theart performance on compressive sensing.”
Nonconvex Nonsmooth Low Rank Minimization via Iteratively Reweighted Nuclear Norm (2015, background): “t be applied to solve (3). The nonconvex low rank matrix completion problem considered in [32] is a special case of our problem (3). Our solver shown later for (3) is also much more general. The work [33] uses the nonconvex log-det heuristic in [34] for image recovery. But their augmented Lagrangian”
Generalized alternating projection based total variation minimization for compressive sensing (2015, methodology): “We test the compressive sensing inversion using GAP-TV on diverse 2D images used in [4,30], with the compressive sensing matrix deﬁned by the permuted Hadamard matrix as used in the real lensless camera [24].”
Rank Minimization for Snapshot Compressive Imaging (2018, methodology): “The group sparsity based algorithms [28] and the nonlocal self-similarity [29] model, which has led to significant advances in image processing, have not been used in these SCI reconstruction algorithms.”
From Denoising to Compressed Sensing (2014, background): “Through extensive simulations we show that in high-dimensional settings (for the subset of denoisers that we consider in this paper) our state evolution predicts the mean square error (MSE) of D-AMP accurately.”
ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Measurements (2016, methodology): “At low measurement rates of 0.1, 0.04 and 0.01, our algorithm yields superior quality reconstructions than the traditional iterative CS reconstruction algorithms, TVAL3, NLR-CS, and D-AMP.”
ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing (2017, methodology): “ploiting the non-local self-similarity properties of natural images have been proposed to improve CS reconstruction [48, 46, 10, 52].”
ADMM-CSNet: A Deep Learning Approach for Image Compressive Sensing (2020, methodology): “Recently, the non-local methods using groups of similar local patches to capture the structural sparsity can better preserve image details [14], [15], [37].”