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 561–570 of 3874 papers

TitleStatusHype
Action Matching: Learning Stochastic Dynamics from SamplesCode1
Efficient Image Super-Resolution using Vast-Receptive-Field AttentionCode1
Rolling Shutter Inversion: Bring Rolling Shutter Images to High Framerate Global Shutter VideoCode1
Single Image Super-Resolution Based on Capsule Neural NetworksCode1
Accurate Image Restoration with Attention Retractable TransformerCode1
From Face to Natural Image: Learning Real Degradation for Blind Image Super-ResolutionCode1
Make-A-Video: Text-to-Video Generation without Text-Video DataCode1
Multi-scale Attention Network for Single Image Super-ResolutionCode1
A heterogeneous group CNN for image super-resolutionCode1
Real-RawVSR: Real-World Raw Video Super-Resolution with a Benchmark DatasetCode1
Show:102550
← PrevPage 57 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified