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 3151–3160 of 3874 papers

TitleStatusHype
Joint Demosaicing and Super-Resolution (JDSR): Network Design and Perceptual Optimization—0
A deep learning framework for morphologic detail beyond the diffraction limit in infrared spectroscopic imagingCode0
Single-Frame Super-Resolution of Solar Magnetograms: Investigating Physics-Based Metrics \& Losses—0
FCSR-GAN: Joint Face Completion and Super-resolution via Multi-task LearningCode0
Probabilistic Super-Resolution of Solar Magnetograms: Generating Many Explanations and Measuring Uncertainties—0
AIM 2019 Challenge on Constrained Super-Resolution: Methods and ResultsCode0
Cross-Scale Residual Network for Multiple Tasks:Image Super-resolution, Denoising, and Deblocking—0
Training Set Effect on Super Resolution for Automated Target Recognition—0
Facial Expression Restoration Based on Improved Graph Convolutional Networks—0
Hyperspectral Super-resolution: A Coupled Nonnegative Block-term Tensor Decomposition Approach—0
Show:102550
← PrevPage 316 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified