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 3361–3370 of 3874 papers

TitleStatusHype
Two-Stream Action Recognition-Oriented Video Super-ResolutionCode0
Universally Slimmable Networks and Improved Training TechniquesCode0
Efficient Deep Neural Network for Photo-realistic Image Super-ResolutionCode0
DepthwiseGANs: Fast Training Generative Adversarial Networks for Realistic Image Synthesis—0
An Adversarial Super-Resolution Remedy for Radar Design Trade-offs—0
Image Super-Resolution by Neural Texture TransferCode0
Meta-SR: A Magnification-Arbitrary Network for Super-ResolutionCode1
A Unified Neural Architecture for Instrumental Audio TasksCode0
Deep Learning for Multiple-Image Super-ResolutionCode0
Two-phase Hair Image Synthesis by Self-Enhancing Generative Model—0
Show:102550
← PrevPage 337 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified