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 1361–1370 of 3874 papers

TitleStatusHype
Symmetric Uncertainty-Aware Feature Transmission for Depth Super-ResolutionCode1
Spatio-Angular Convolutions for Super-resolution in Diffusion MRICode0
Dissecting Arbitrary-scale Super-resolution Capability from Pre-trained Diffusion Generative Models—0
Physics-Informed Ensemble Representation for Light-Field Image Super-ResolutionCode0
Toward Real-World Light Field Super-ResolutionCode0
Scale-aware Super-resolution Network with Dual Affinity Learning for Lesion Segmentation from Medical Images—0
Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution—0
Convolutional neural network based on sparse graph attention mechanism for MRI super-resolution—0
USIM-DAL: Uncertainty-aware Statistical Image Modeling-based Dense Active Learning for Super-resolution—0
Super-Resolution of License Plate Images Using Attention Modules and Sub-Pixel Convolution LayersCode1
Show:102550
← PrevPage 137 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified