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 951–960 of 3874 papers

TitleStatusHype
Scene Text Image Super-Resolution in the WildCode1
NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and ResultsCode1
Deep Generative Adversarial Residual Convolutional Networks for Real-World Super-ResolutionCode1
On Solving SAR Imaging Inverse Problems Using Non-Convex Regularization with a Cauchy-based PenaltyCode1
MeshfreeFlowNet: A Physics-Constrained Deep Continuous Space-Time Super-Resolution FrameworkCode1
Pyramid Attention Networks for Image RestorationCode1
Deploying Image Deblurring across Mobile Devices: A Perspective of Quality and LatencyCode1
Unsupervised Real Image Super-Resolution via Generative Variational AutoEncoderCode1
Deep Interleaved Network for Image Super-Resolution With Asymmetric Co-AttentionCode1
Microscopy Image Restoration using Deep Learning on W2SCode1
Show:102550
← PrevPage 96 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified