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 991–1000 of 3874 papers

TitleStatusHype
Model-Guided Multi-Contrast Deep Unfolding Network for MRI Super-resolution ReconstructionCode1
Diffusion-based Blind Text Image Super-ResolutionCode1
Blueprint Separable Residual Network for Efficient Image Super-ResolutionCode1
An efficient CNN for spectral reconstruction from RGB imagesCode1
Diffusion Model Based Posterior Sampling for Noisy Linear Inverse ProblemsCode1
MegaSR: Mining Customized Semantics and Expressive Guidance for Image Super-ResolutionCode1
Towards Real Scene Super-Resolution with Raw ImagesCode1
Towards Real-Time 4K Image Super-ResolutionCode1
DSR: Towards Drone Image Super-ResolutionCode1
Diffusion Models Beat GANs on Image ClassificationCode1
Show:102550
← PrevPage 100 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified