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 2371–2380 of 3874 papers

TitleStatusHype
Trustworthy modelling of atmospheric formaldehyde powered by deep learning—0
Extreme-scale Talking-Face Video Upsampling with Audio-Visual PriorsCode0
Multi-dimensional topological loss for cortical plate segmentation in fetal brain MRI—0
Urban precipitation downscaling using deep learning: a smart city application over Austin, Texas, USA—0
An Adversarial Generative Network Designed for High-Resolution Monocular Depth Estimation from 2D HiRISE Images of MarsCode0
Global Priors Guided Modulation Network for Joint Super-Resolution and Inverse Tone-Mapping—0
G-PCC Post-Processing Using Fractional Super-Resolution—0
Online Video Super-Resolution with Convolutional Kernel Bypass Graft—0
H2-Stereo: High-Speed, High-Resolution Stereoscopic Video System—0
Latent Multi-Relation Reasoning for GAN-Prior based Image Super-Resolution—0
Show:102550
← PrevPage 238 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified