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 2191–2200 of 3874 papers

TitleStatusHype
Neural Prior for Trajectory Estimation—0
Pix2NeRF: Unsupervised Conditional p-GAN for Single Image to Neural Radiance Fields TranslationCode2
Efficient Single Image Super-Resolution Using Dual Path Connections with Multiple Scale LearningCode1
A Resolution Enhancement Plug-in for Deformable Registration of Medical Images—0
HPRN: Holistic Prior-embedded Relation Network for Spectral Super-ResolutionCode0
Super-Efficient Super Resolution for Fast Adversarial Defense at the EdgeCode0
Astronomical Image Colorization and upscaling with Generative Adversarial Networks—0
DSRGAN: Detail Prior-Assisted Perceptual Single Image Super-Resolution via Generative Adversarial Networks—0
Reflash Dropout in Image Super-ResolutionCode1
Implicit Neural Representation Learning for Hyperspectral Image Super-Resolution—0
Show:102550
← PrevPage 220 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified