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 921–930 of 3874 papers

TitleStatusHype
Lightweight Modules for Efficient Deep Learning based Image RestorationCode1
Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-ResolutionCode1
Lightweight image super-resolution with enhanced CNNCode1
Journey Towards Tiny Perceptual Super-ResolutionCode1
Light Field Image Super-Resolution Using Deformable ConvolutionCode1
Multi-image Super Resolution of Remotely Sensed Images using Residual Feature Attention Deep Neural NetworksCode1
BiO-Net: Learning Recurrent Bi-directional Connections for Encoder-Decoder ArchitectureCode1
Cross-Scale Internal Graph Neural Network for Image Super-ResolutionCode1
SRFlow: Learning the Super-Resolution Space with Normalizing FlowCode1
iSeeBetter: Spatio-Temporal Video Super Resolution using Recurrent-Generative Back-Projection NetworksCode1
Show:102550
← PrevPage 93 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified