SOTAVerified

Compressive Sensing

Compressive Sensing is a new signal processing framework for efficiently acquiring and reconstructing a signal that have a sparse representation in a fixed linear basis.

Source: Sparse Estimation with Generalized Beta Mixture and the Horseshoe Prior

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 311–320 of 597 papers

TitleStatusHype
Model-Aware Deep Architectures for One-Bit Compressive Variational AutoencodingCode0
Deep Decomposition Learning for Inverse Imaging ProblemsCode0
Nonconvex Nonsmooth Low-Rank Minimization for Generalized Image Compressed Sensing via Group Sparse Representation—0
Convex Reconstruction of Structured Matrix Signals from Linear Measurements (I): Theoretical Results—0
Structure Preserving Compressive Sensing MRI Reconstruction using Generative Adversarial NetworksCode0
Lipschitz Learning for Signal Recovery—0
Removing the Representation Error of GAN Image Priors Using the Deep Decoder—0
IFR-Net: Iterative Feature Refinement Network for Compressed Sensing MRICode0
Difference of Convolution for Deep Compressive SensingCode0
On reconstruction algorithms for signals sparse in Hermite and Fourier domains—0
Show:102550
← PrevPage 32 of 60Next →
All datasetsSet11 cs=50%BSD68 CS=50%BSDS100 - 2x upscalingUrban100 - 2x upscaling

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DMP-DUN-Plus (4-step)Average PSNR42.82—Unverified
2AMPA-NetAverage PSNR40.32—Unverified
#ModelMetricClaimedVerifiedStatus
1AMPA-NetAverage PSNR36.33—Unverified
#ModelMetricClaimedVerifiedStatus
1AMPA-NetAverage PSNR35.95—Unverified
#ModelMetricClaimedVerifiedStatus
1AMPA-NetAverage PSNR35.86—Unverified