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 3781–3790 of 3874 papers

TitleStatusHype
Attention Based Real Image RestorationCode0
Attention-based Multi-Reference Learning for Image Super-ResolutionCode0
Robust Deep Ensemble Method for Real-world Image DenoisingCode0
AtlasNet: A Papier-Mâché Approach to Learning 3D Surface GenerationCode0
Deep Learning for Cornea Microscopy Blind DeblurringCode0
Zoomed In, Diffused Out: Towards Local Degradation-Aware Multi-Diffusion for Extreme Image Super-ResolutionCode0
Style Transfer and Self-Supervised Learning Powered Myocardium Infarction Super-Resolution SegmentationCode0
Accelerating the Training of Video Super-Resolution ModelsCode0
Sub-frame Appearance and 6D Pose Estimation of Fast Moving ObjectsCode0
FSRNet: End-to-End Learning Face Super-Resolution with Facial PriorsCode0
Show:102550
← PrevPage 379 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified