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 171–180 of 3874 papers

TitleStatusHype
Enhancing Image Resolution of Solar Magnetograms: A Latent Diffusion Model ApproachCode0
A Lightweight Image Super-Resolution Transformer Trained on Low-Resolution Images OnlyCode0
DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution—0
A GAN-Enhanced Deep Learning Framework for Rooftop Detection from Historical Aerial ImageryCode0
Knowledge Rectification for Camouflaged Object Detection: Unlocking Insights from Low-Quality Data—0
Deterministic Medical Image Translation via High-fidelity Brownian Bridges—0
Evaluation of Machine-generated Biomedical Images via A Tally-based Similarity Measure—0
RELD: Regularization by Latent Diffusion Models for Image Restoration—0
KernelFusion: Assumption-Free Blind Super-Resolution via Patch Diffusion—0
Simulation-informed deep learning for enhanced SWOT observations of fine-scale ocean dynamics—0
Show:102550
← PrevPage 18 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified