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 2141–2150 of 3874 papers

TitleStatusHype
Synthesizing Realistic Image Restoration Training Pairs: A Diffusion Approach—0
IFF: A Super-resolution Algorithm for Multiple Measurements—0
Raising The Limit Of Image Rescaling Using Auxiliary Encoding—0
DDS2M: Self-Supervised Denoising Diffusion Spatio-Spectral Model for Hyperspectral Image Restoration—0
CoT-MISR:Marrying Convolution and Transformer for Multi-Image Super-Resolution—0
MLP-SRGAN: A Single-Dimension Super Resolution GAN using MLP-MixerCode0
A New Super-Resolution Measurement of Perceptual Quality and Fidelity—0
Handheld Burst Super-Resolution Meets Multi-Exposure Satellite Imagery—0
Provably Convergent Plug-and-Play Quasi-Newton MethodsCode0
EfficientTempNet: Temporal Super-Resolution of Radar Rainfall—0
Show:102550
← PrevPage 215 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified