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 3521–3530 of 3874 papers

TitleStatusHype
LCSCNet: Linear Compressing Based Skip-Connecting Network for Image Super-ResolutionCode0
Wavelet Flow: Fast Training of High Resolution Normalizing FlowsCode0
LatticeNet: Towards Lightweight Image Super-resolution with Lattice BlockCode0
ECLARE: Efficient cross-planar learning for anisotropic resolution enhancementCode0
Small or Far Away? Exploiting Deep Super-Resolution and Altitude Data for Aerial Animal SurveillanceCode0
Latent Diffusion, Implicit Amplification: Efficient Continuous-Scale Super-Resolution for Remote Sensing ImagesCode0
SRECG: ECG Signal Super-resolution Framework for Portable/Wearable Devices in Cardiac Arrhythmias ClassificationCode0
Polynomial-time Sparse Measure Recovery: From Mean Field Theory to Algorithm DesignCode0
A Review of Convolutional Neural Networks for Inverse Problems in ImagingCode0
Unpaired Depth Super-Resolution in the WildCode0
Show:102550
← PrevPage 353 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified