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

Showing 37213730 of 3874 papers

TitleStatusHype
An Efficient Network Design for Face Video Super-resolutionCode0
HSTR-Net: High Spatio-Temporal Resolution Video Generation For Wide Area SurveillanceCode0
Deep Sparse and Low-Rank Prior for Hyperspectral Image DenoisingCode0
Deep Residual Network for Joint Demosaicing and Super-ResolutionCode0
A Unified Neural Architecture for Instrumental Audio TasksCode0
Residual Dense Network for Image RestorationCode0
Residual Dense Network for Image Super-ResolutionCode0
HR-INR: Continuous Space-Time Video Super-Resolution via Event CameraCode0
Deep Mean-Shift Priors for Image RestorationCode0
HPRN: Holistic Prior-embedded Relation Network for Spectral Super-ResolutionCode0
Show:102550
← PrevPage 373 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41Unverified