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 671–680 of 3874 papers

TitleStatusHype
Ad2Attack: Adaptive Adversarial Attack on Real-Time UAV TrackingCode1
Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed ObservationsCode1
Spatio-temporal Vision Transformer for Super-resolution MicroscopyCode1
Conditional Simulation Using Diffusion Schrödinger BridgesCode1
Convolutional Neural Network Modelling for MODIS Land Surface Temperature Super-ResolutionCode1
Computing Multiple Image Reconstructions with a Single HypernetworkCode1
Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in ImagingCode1
TR-MISR: Multiimage Super-Resolution Based on Feature Fusion With TransformersCode1
Gradient Variance Loss for Structure-Enhanced Image Super-ResolutionCode1
Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex RegularizationCode1
Show:102550
← PrevPage 68 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified