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 2351–2360 of 3874 papers

TitleStatusHype
Memory-Augmented Non-Local Attention for Video Super-ResolutionCode1
edge-SR: Super-Resolution For The MassesCode1
SwinIR: Image Restoration Using Swin TransformerCode3
Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search—0
Thermal Image Processing via Physics-Inspired Deep NetworksCode1
Deep Reparametrization of Multi-Frame Super-Resolution and DenoisingCode1
Temporal Kernel Consistency for Blind Video Super-Resolution—0
Light Field Image Super-Resolution with TransformersCode1
spectrai: A deep learning framework for spectral dataCode1
SURFNet: Super-resolution of Turbulent Flows with Transfer Learning using Small Datasets—0
Show:102550
← PrevPage 236 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified