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 1961–1970 of 3874 papers

TitleStatusHype
Dynamic Structured Illumination Microscopy with a Neural Space-time ModelCode0
Super-resolving 2D stress tensor field conserving equilibrium constraints using physics informed U-Net—0
Efficient Multi-Purpose Cross-Attention Based Image Alignment Block for Edge Devices—0
ShuffleMixer: An Efficient ConvNet for Image Super-ResolutionCode1
Deep Posterior Distribution-based Embedding for Hyperspectral Image Super-resolutionCode1
Image Super-resolution with An Enhanced Group Convolutional Neural NetworkCode1
EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense PredictionCode4
Enhancing Quality of Pose-varied Face Restoration with Local Weak Feature Sensing and GAN Prior—0
Textural-Perceptual Joint Learning for No-Reference Super-Resolution Image Quality AssessmentCode0
Image Reconstruction of Multi Branch Feature Multiplexing Fusion Network with Mixed Multi-layer Attention—0
Show:102550
← PrevPage 197 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified