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 571–580 of 3874 papers

TitleStatusHype
Face Super-Resolution Using Stochastic Differential EquationsCode1
HAZE-Net: High-Frequency Attentive Super-Resolved Gaze Estimation in Low-Resolution Face ImagesCode1
KXNet: A Model-Driven Deep Neural Network for Blind Super-ResolutionCode1
Deep Plug-and-Play Prior for Hyperspectral Image RestorationCode1
Model-Guided Multi-Contrast Deep Unfolding Network for MRI Super-resolution ReconstructionCode1
Generative Adversarial Super-Resolution at the Edge with Knowledge DistillationCode1
Joint Learning Content and Degradation Aware Feature for Blind Super-ResolutionCode1
DSR: Towards Drone Image Super-ResolutionCode1
SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-ResolutionCode1
RZSR: Reference-based Zero-Shot Super-Resolution with Depth Guided Self-ExemplarsCode1
Show:102550
← PrevPage 58 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified