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 1911–1920 of 3874 papers

TitleStatusHype
Face Super-Resolution with Progressive Embedding of Multi-scale Face Priors—0
Joint Demosaicing and Super-Resolution (JDSR): Network Design and Perceptual Optimization—0
Content-adaptive Representation Learning for Fast Image Super-resolution—0
Joint Estimation of Camera Pose, Depth, Deblurring, and Super-Resolution from a Blurred Image Sequence—0
Joint Face Completion and Super-resolution using Multi-scale Feature Relation Learning—0
Joint Face Hallucination and Deblurring via Structure Generation and Detail Enhancement—0
Joint Face Super-Resolution and Deblurring Using a Generative Adversarial Network—0
Joint Flow And Feature Refinement Using Attention For Video Restoration—0
Suppressing Model Overfitting for Image Super-Resolution Networks—0
Face Super-resolution Guided by Facial Component Heatmaps—0
Show:102550
← PrevPage 192 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified