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 2451–2460 of 3874 papers

TitleStatusHype
Feedback Pyramid Attention Networks for Single Image Super-Resolution—0
Video Super-Resolution TransformerCode1
Task Transformer Network for Joint MRI Reconstruction and Super-ResolutionCode1
Catch-A-Waveform: Learning to Generate Audio from a Single Short ExampleCode1
A self-adapting super-resolution structures framework for automatic design of GAN—0
Super-Resolution Image Reconstruction Based on Self-Calibrated Convolutional GAN—0
Variational AutoEncoder for Reference based Image Super-ResolutionCode1
NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results—0
Deep Neural Network-based Enhancement for Image and Video Streaming Systems: A Survey and Future Directions—0
Noise Conditional Flow Model for Learning the Super-Resolution SpaceCode1
Show:102550
← PrevPage 246 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified