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 1691–1700 of 3874 papers

TitleStatusHype
A New Multi-Picture Architecture for Learned Video Deinterlacing and Demosaicing with Parallel Deformable Convolution and Self-Attention BlocksCode0
VideoGigaGAN: Towards Detail-rich Video Super-Resolution—0
OmniSSR: Zero-shot Omnidirectional Image Super-Resolution using Stable Diffusion Model—0
Little Pilot is Needed for Channel Estimation with Integrated Super-Resolution Sensing and Communication—0
Super-resolution of biomedical volumes with 2D supervision—0
MTKD: Multi-Teacher Knowledge Distillation for Image Super-Resolution—0
Differentiable Search for Finding Optimal Quantization Strategy—0
Unfolding ADMM for Enhanced Subspace Clustering of Hyperspectral ImagesCode0
Diffusion-Based Point Cloud Super-Resolution for mmWave Radar Data—0
Space-Time Video Super-resolution with Neural Operator—0
Show:102550
← PrevPage 170 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified