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 3701–3710 of 3874 papers

TitleStatusHype
Single Image Super-Resolution based on Wiener Filter in Similarity Domain—0
Deep Laplacian Pyramid Networks for Fast and Accurate Super-ResolutionCode0
Detail-revealing Deep Video Super-resolutionCode0
Locally-adapted convolution-based super-resolution of irregularly-sampled ocean remote sensing data—0
Isotropic reconstruction of 3D fluorescence microscopy images using convolutional neural networks—0
Single Image Super Resolution - When Model Adaptation Matters—0
Image Restoration using Autoencoding Priors—0
One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection ModelsCode0
CVAE-GAN: Fine-Grained Image Generation through Asymmetric TrainingCode1
Learned Spectral Super-ResolutionCode1
Show:102550
← PrevPage 371 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified