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 3121–3130 of 3874 papers

TitleStatusHype
Correction Filter for Single Image Super-Resolution: Robustifying Off-the-Shelf Deep Super-ResolversCode0
Learning Likelihoods with Conditional Normalizing FlowsCode0
Learning from Irregularly Sampled Data for Endomicroscopy Super-resolution: A Comparative Study of Sparse and Dense Approaches—0
Quality analysis of DCGAN-generated mammography lesions—0
Neural Network-Inspired Analog-to-Digital Conversion to Achieve Super-Resolution with Low-Precision RRAM Devices—0
Super-Resolution for Practical Automated Plant Disease Diagnosis System—0
Using Physics-Informed Super-Resolution Generative Adversarial Networks for Subgrid Modeling in Turbulent Reactive Flows—0
FAN: Feature Adaptation Network for Surveillance Face Recognition and Normalization—0
Deep Decomposition Learning for Inverse Imaging ProblemsCode0
Cascaded Detail-Preserving Networks for Super-Resolution of Document Images—0
Show:102550
← PrevPage 313 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified