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 2151–2160 of 3874 papers

TitleStatusHype
VRT: A Video Restoration TransformerCode3
Denoising Diffusion Restoration ModelsCode2
Revisiting RCAN: Improved Training for Image Super-ResolutionCode1
Learning Multiple Probabilistic Degradation Generators for Unsupervised Real World Image Super ResolutionCode0
Revisiting L1 Loss in Super-Resolution: A Probabilistic View and Beyond—0
Hyperspectral Image Super-resolution with Deep Priors and Degradation Model InversionCode1
Perceptual cGAN for MRI Super-resolutionCode0
A Review of Deep Learning Based Image Super-resolution Techniques—0
Robust Unpaired Single Image Super-Resolution of Faces—0
SparseAlign: A Super-Resolution Algorithm for Automatic Marker Localization and Deformation Estimation in Cryo-Electron Tomography—0
Show:102550
← PrevPage 216 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified