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 11711180 of 3874 papers

TitleStatusHype
MLP-SRGAN: A Single-Dimension Super Resolution GAN using MLP-MixerCode0
Multigrid Backprojection Super-Resolution and Deep Filter VisualizationCode0
Deep Learning for Image Super-resolution: A SurveyCode0
Algorithmic Guarantees for Inverse Imaging with Untrained Network PriorsCode0
Deep Learning for Cornea Microscopy Blind DeblurringCode0
MemNet: A Persistent Memory Network for Image RestorationCode0
MetH: A family of high-resolution and variable-shape image challengesCode0
A Learning-Based Framework for Line-Spectra Super-resolutionCode0
MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and EnhancementCode0
Deep learning-based super-resolution fluorescence microscopy on small datasetsCode0
Show:102550
← PrevPage 118 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41Unverified