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 3751–3760 of 3874 papers

TitleStatusHype
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural NetworkCode1
Transport-based analysis, modeling, and learning from signal and data distributions—0
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial NetworkCode1
Sampling Generative NetworksCode1
A Boosting Method to Face Image Super-resolution—0
Confidence-aware Levenberg-Marquardt optimization for joint motion estimation and super-resolution—0
Constraint matrix factorization for space variant PSFs field restorationCode0
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image DenoisingCode1
Accelerating the Super-Resolution Convolutional Neural NetworkCode1
New wavelet-based superresolution algorithm for speckle reduction in SAR images—0
Show:102550
← PrevPage 376 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified