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 2471–2480 of 3874 papers

TitleStatusHype
Generative Adversarial Networks for Image Super-Resolution: A Survey—0
Gridless Tomographic SAR Imaging Based on Accelerated Atomic Norm Minimization with Efficiency—0
IMDeception: Grouped Information Distilling Super-Resolution Network—0
Unsupervised Blur Kernel Estimation and Correction for Blind Super-ResolutionCode0
NTIRE 2022 Challenge on Stereo Image Super-Resolution: Methods and Results—0
FS-NCSR: Increasing Diversity of the Super-Resolution Space via Frequency Separation and Noise-Conditioned Normalizing FlowCode0
Learning Enriched Features for Fast Image Restoration and Enhancement—0
Unsupervised domain adaptation and super resolution on drone images for autonomous dry herbage biomass estimationCode0
Semi-Supervised Super-Resolution—0
Polynomial-time Sparse Measure Recovery: From Mean Field Theory to Algorithm DesignCode0
Show:102550
← PrevPage 248 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified