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 3041–3050 of 3874 papers

TitleStatusHype
Self-supervised Fine-tuning for Correcting Super-Resolution Convolutional Neural Networks—0
Applying VertexShuffle Toward 360-Degree Video Super-Resolution on Focused-Icosahedral-Mesh—0
Applying Physics-Informed Enhanced Super-Resolution Generative Adversarial Networks to Turbulent Premixed Combustion and Engine-like Flame Kernel Direct Numerical Simulation Data—0
Applying Physics-Informed Enhanced Super-Resolution Generative Adversarial Networks to Finite-Rate-Chemistry Flows and Predicting Lean Premixed Gas Turbine Combustors—0
Self-Supervised Learning with Generative Adversarial Networks for Electron Microscopy—0
Self-supervised Recurrent Neural Network for 4D Abdominal and In-utero MR Imaging—0
Self-Supervised Super-Resolution Approach for Isotropic Reconstruction of 3D Electron Microscopy Images from Anisotropic Acquisition—0
Self-Supervised Super-Resolution for Multi-Exposure Push-Frame Satellites—0
Self-Tuned Deep Super Resolution—0
Semantically Accurate Super-Resolution Generative Adversarial Networks—0
Show:102550
← PrevPage 305 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified