SOTAVerified

Super-Resolution

Super-Resolution is a task in computer vision that involves increasing the resolution of an image or video by generating missing high-frequency details from low-resolution input. The goal is to produce an output image with a higher resolution than the input image, while preserving the original content and structure.

( Credit: MemNet )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 3581–3590 of 3874 papers

TitleStatusHype
Residual Dense Network for Image Super-ResolutionCode0
MagnifyMe: Aiding Cross Resolution Face Recognition via Identity Aware Synthesis—0
Composite Optimization by Nonconvex Majorization-Minimization—0
Deep Residual Network for Joint Demosaicing and Super-ResolutionCode0
cGANs with Projection DiscriminatorCode0
Learning from a Handful Volumes: MRI Resolution Enhancement with Volumetric Super-Resolution ForestsCode0
AtlasNet: A Papier-Mâché Approach to Learning 3D Surface GenerationCode0
Image Transformer—0
Quantifying Uncertainty in Discrete-Continuous and Skewed Data with Bayesian Deep LearningCode0
Deep Image Super Resolution via Natural Image Priors—0
Show:102550
← PrevPage 359 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified