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 3011–3020 of 3874 papers

TitleStatusHype
Learning to Learn to Compress—0
Very Deep Super-Resolution of Remotely Sensed Images with Mean Square Error and Var-norm Estimators as Loss Functions—0
Sparse Based Super Resolution Multilayer Ultrasonic Array Imaging—0
Accurate Lung Nodules Segmentation with Detailed Representation Transfer and Soft Mask Supervision—0
Video compression with low complexity CNN-based spatial resolution adaptation—0
Coupled Convolutional Neural Network with Adaptive Response Function Learning for Unsupervised Hyperspectral Super-ResolutionCode0
Efficient OCT Image Segmentation Using Neural Architecture Search—0
Deep learning Framework for Mobile MicroscopyCode0
Video Super Resolution Based on Deep Learning: A Comprehensive Survey—0
T2 Mapping from Super-Resolution-Reconstructed Clinical Fast Spin Echo Magnetic Resonance Acquisitions—0
Show:102550
← PrevPage 302 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified