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 491–500 of 3874 papers

TitleStatusHype
Learning multi-scale local conditional probability models of imagesCode1
BrainBERT: Self-supervised representation learning for intracranial recordingsCode1
Learning to Super-Resolve Blurry Images with EventsCode1
Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded ImagesCode1
A residual dense vision transformer for medical image super-resolution with segmentation-based perceptual loss fine-tuningCode1
Improving Scene Text Image Super-resolution via Dual Prior Modulation NetworkCode1
LIT-Former: Linking In-plane and Through-plane Transformers for Simultaneous CT Image Denoising and DeblurringCode1
RecFNO: a resolution-invariant flow and heat field reconstruction method from sparse observations via Fourier neural operatorCode1
Guided Depth Map Super-resolution: A SurveyCode1
Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-ResolutionCode1
Show:102550
← PrevPage 50 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified