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 3101–3110 of 3874 papers

TitleStatusHype
ΩSFormer: Dual-Modal Ω-like Super-Resolution Transformer Network for Cross-scale and High-accuracy Terraced Field Vectorization Extraction—0
One-shot Ultra-high-Resolution Generative Adversarial Network That Synthesizes 16K Images On A Single GPU—0
Overparametrization of HyperNetworks at Fixed FLOP-Count Enables Fast Neural Image Enhancement—0
Over-the-Air Time-Frequency Synchronization in Distributed ISAC Systems—0
Padding-free Convolution based on Preservation of Differential Characteristics of Kernels—0
PAG-Net: Progressive Attention Guided Depth Super-resolution Network—0
PanFlowNet: A Flow-Based Deep Network for Pan-sharpening—0
Panoramas from Photons—0
PAON: A New Neuron Model using Padé Approximants—0
ParaDiS: Parallelly Distributable Slimmable Neural Networks—0
Show:102550
← PrevPage 311 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified