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 831–840 of 3874 papers

TitleStatusHype
Dynamic Implicit Image Function for Efficient Arbitrary-Scale Image RepresentationCode1
DynaVSR: Dynamic Adaptive Blind Video Super-ResolutionCode1
ECAMP: Entity-centered Context-aware Medical Vision Language Pre-trainingCode1
DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution ModelsCode1
One Step Diffusion-based Super-Resolution with Time-Aware DistillationCode1
Dual-Stage Approach Toward Hyperspectral Image Super-ResolutionCode1
Deep learning architectural designs for super-resolution of noisy imagesCode1
On Measuring and Controlling the Spectral Bias of the Deep Image PriorCode1
Dual-Diffusion: Dual Conditional Denoising Diffusion Probabilistic Models for Blind Super-Resolution Reconstruction in RSIsCode1
Dual Super-Resolution Learning for Semantic SegmentationCode1
Show:102550
← PrevPage 84 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified