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 3481–3490 of 3874 papers

TitleStatusHype
Photometric Depth Super-ResolutionCode0
Super-Resolution using Convolutional Neural Networks without Any Checkerboard ArtifactsCode0
Efficient Deep Neural Network for Photo-realistic Image Super-ResolutionCode0
Learning to Super Resolve Intensity Images from EventsCode0
Adaptive Densely Connected Super-Resolution ReconstructionCode0
Deep Decomposition Learning for Inverse Imaging ProblemsCode0
Brain MRI super-resolution using 3D generative adversarial networksCode0
Physics-Informed CNNs for Super-Resolution of Sparse Observations on Dynamical SystemsCode0
A Lightweight Recurrent Grouping Attention Network for Video Super-ResolutionCode0
Learning Series-Parallel Lookup Tables for Efficient Image Super-ResolutionCode0
Show:102550
← PrevPage 349 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified