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 791–800 of 3874 papers

TitleStatusHype
Multi-Contrast MRI Super-Resolution via a Multi-Stage Integration NetworkCode1
Parallel and Flexible Sampling from Autoregressive Models via Langevin DynamicsCode1
Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: ReportCode1
Image Super-Resolution Quality Assessment: Structural Fidelity Versus Statistical NaturalnessCode1
End-to-end Alternating Optimization for Blind Super ResolutionCode1
EDPN: Enhanced Deep Pyramid Network for Blurry Image RestorationCode1
Differentiable Neural Architecture Search for Extremely Lightweight Image Super-ResolutionCode1
Unsupervised Remote Sensing Super-Resolution via Migration Image PriorCode1
Infrared Image Super-Resolution via Transfer Learning and PSRGANCode1
Brain Graph Super-Resolution Using Adversarial Graph Neural Network with Application to Functional Brain ConnectivityCode1
Show:102550
← PrevPage 80 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified