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 3511–3520 of 3874 papers

TitleStatusHype
Spatio-temporal Transformer Network for Video Restoration—0
Learning Sparse Low-Precision Neural Networks With Learnable Regularization—0
Super-Resolution and Sparse View CT Reconstruction—0
Super-Resolution for Hyperspectral and Multispectral Image Fusion Accounting for Seasonal Spectral Variability—0
Deeply Supervised Depth Map Super-Resolution as Novel View Synthesis—0
Wide Activation for Efficient and Accurate Image Super-ResolutionCode0
Efficient Single Image Super Resolution using Enhanced Learned Group ConvolutionsCode0
MSCE: An edge preserving robust loss function for improving super-resolution algorithms—0
Improving Super-Resolution Methods via Incremental Residual LearningCode0
Medical Image Imputation from Image CollectionsCode0
Show:102550
← PrevPage 352 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified