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 2971–2980 of 3874 papers

TitleStatusHype
A self-adapting super-resolution structures framework for automatic design of GAN—0
AsConvSR: Fast and Lightweight Super-Resolution Network with Assembled Convolutions—0
Sampling Based Scene-Space Video Processing—0
A Scale-Arbitrary Image Super-Resolution Network Using Frequency-domain Information—0
Generative Imaging and Image Processing via Generative Encoder—0
SASNet: Spatially-Adaptive Sinusoidal Neural Networks—0
SatDiffMoE: A Mixture of Estimation Method for Satellite Image Super-resolution with Latent Diffusion Models—0
Satellite Image Small Target Application Based on Deep Segmented Residual Neural Network—0
SATVSR: Scenario Adaptive Transformer for Cross Scenarios Video Super-Resolution—0
Scalable image coding based on epitomes—0
Show:102550
← PrevPage 298 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified