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 3761–3770 of 3874 papers

TitleStatusHype
GhostSR: Learning Ghost Features for Efficient Image Super-ResolutionCode0
Structured illumination microscopy image reconstruction algorithmCode0
Coupled Convolutional Neural Network with Adaptive Response Function Learning for Unsupervised Hyperspectral Super-ResolutionCode0
Geometry aware inference of steady state PDEs using Equivariant Neural Fields representationsCode0
Correspondence Transformers With Asymmetric Feature Learning and Matching Flow Super-ResolutionCode0
Deep Learning for Multiple-Image Super-ResolutionCode0
Generative Collaborative Networks for Single Image Super-ResolutionCode0
Generative Adversarial Networks: An OverviewCode0
Deep Learning for Image Super-resolution: A SurveyCode0
Generative adversarial network-based image super-resolution using perceptual content lossesCode0
Show:102550
← PrevPage 377 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified