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 1741–1750 of 3874 papers

TitleStatusHype
Identity-Preserving Pose-Robust Face Hallucination Through Face Subspace Prior—0
IEGAN: Multi-purpose Perceptual Quality Image Enhancement Using Generative Adversarial Network—0
FastSR-NeRF: Improving NeRF Efficiency on Consumer Devices with A Simple Super-Resolution Pipeline—0
Fast Spatio-Temporal Residual Network for Video Super-Resolution—0
Fast single image super-resolution based on sigmoid transformation—0
Convolutional neural network based on sparse graph attention mechanism for MRI super-resolution—0
Inverting a Rolling Shutter Camera: Bring Rolling Shutter Images to High Framerate Global Shutter Video—0
Fast Single Image Super-Resolution—0
Image Deconvolution with Deep Image and Kernel Priors—0
Convolutional Low-Resolution Fine-Grained Classification—0
Show:102550
← PrevPage 175 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified