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 3161–3170 of 3874 papers

TitleStatusHype
Image Restoration Using Deep Regulated Convolutional NetworksCode0
Component Attention Guided Face Super-Resolution Network: CAGFaceCode0
Image Deconvolution with Deep Image and Kernel Priors—0
Multimodal Image Super-resolution via Deep Unfolding with Side Information—0
Translation position extracting in incoherent Fourier ptychography—0
ERNet Family: Hardware-Oriented CNN Models for Computational Imaging Using Block-Based Inference—0
eCNN: A Block-Based and Highly-Parallel CNN Accelerator for Edge Inference—0
Image Super-Resolution via Attention based Back Projection NetworksCode0
Practical License Plate Recognition in Unconstrained Surveillance Systems with Adversarial Super-ResolutionCode0
Deep Convolutional Neural Network for Multi-modal Image Restoration and Fusion—0
Show:102550
← PrevPage 317 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified