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 3171–3180 of 3874 papers

TitleStatusHype
Wavelet Domain Style Transfer for an Effective Perception-distortion Tradeoff in Single Image Super-ResolutionCode0
Unsupervised Image Super-Resolution with an Indirect Supervised Path—0
Image Super-Resolution Improved by Edge InformationCode0
High-dimensional Dense Residual Convolutional Neural Network for Light Field ReconstructionCode1
Better to Follow, Follow to Be Better: Towards Precise Supervision of Feature Super-Resolution for Small Object Detection—0
Progressive Fusion Video Super-Resolution Network via Exploiting Non-Local Spatio-Temporal CorrelationsCode0
Fast Image Restoration With Multi-Bin Trainable Linear UnitsCode0
Embedded Block Residual Network: A Recursive Restoration Model for Single-Image Super-Resolution—0
Deep Blind Hyperspectral Image Fusion—0
Kernel Modeling Super-Resolution on Real Low-Resolution ImagesCode0
Show:102550
← PrevPage 318 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified