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 3771–3780 of 3874 papers

TitleStatusHype
Generative Adversarial Models for Extreme Geospatial Downscaling—0
TextureWGAN: Texture Preserving WGAN with MLE Regularizer for Inverse Problems—0
Generative adversarial network for super-resolution imaging through a fiber—0
SCALES: Boost Binary Neural Network for Image Super-Resolution with Efficient Scalings—0
Generative Adversarial Networks and Perceptual Losses for Video Super-Resolution—0
Super-Resolution Generative Adversarial Networks based Video Enhancement—0
Generative Adversarial Networks for Image Super-Resolution: A Survey—0
EAM: Enhancing Anything with Diffusion Transformers for Blind Super-Resolution—0
Generative AI in Vision: A Survey on Models, Metrics and Applications—0
A Dive into SAM Prior in Image Restoration—0
Show:102550
← PrevPage 378 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified