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 3531–3540 of 3874 papers

TitleStatusHype
Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion CompensationCode0
“Zero-Shot” Super-Resolution Using Deep Internal Learning—0
Feature Super-Resolution: Make Machine See More Clearly—0
Scale-Transferrable Object Detection—0
Super-Resolving Very Low-Resolution Face Images With Supplementary Attributes—0
A Papier-Mâché Approach to Learning 3D Surface Generation—0
Fight Ill-Posedness With Ill-Posedness: Single-Shot Variational Depth Super-Resolution From ShadingCode0
On Low-Resolution Face Recognition in the Wild: Comparisons and New Techniques—0
Face Recognition in Low Quality Images: A Survey—0
Face hallucination using cascaded super-resolution and identity priors—0
Show:102550
← PrevPage 354 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified