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 651–660 of 3874 papers

TitleStatusHype
Conditional Hyper-Network for Blind Super-Resolution with Multiple DegradationsCode1
Diffusion-based Blind Text Image Super-ResolutionCode1
Deformable 3D Convolution for Video Super-ResolutionCode1
Conditional Simulation Using Diffusion Schrödinger BridgesCode1
Conditional Variational Diffusion ModelsCode1
Crack Segmentation for Low-Resolution Images using Joint Learning with Super-ResolutionCode1
A Systematic Survey of Deep Learning-based Single-Image Super-ResolutionCode1
From Coarse to Fine: Hierarchical Pixel Integration for Lightweight Image Super-ResolutionCode1
Conffusion: Confidence Intervals for Diffusion ModelsCode1
DeFMO: Deblurring and Shape Recovery of Fast Moving ObjectsCode1
Show:102550
← PrevPage 66 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified