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 3541–3550 of 3874 papers

TitleStatusHype
Accurate Spectral Super-resolution from Single RGB Image Using Multi-scale CNN—0
Non-Local Recurrent Network for Image RestorationCode0
Super-Resolution using Convolutional Neural Networks without Any Checkerboard ArtifactsCode0
Adaptive Importance Learning for Improving Lightweight Image Super-resolution Network—0
Patch-Based Image Hallucination for Super Resolution with Detail Reconstruction from Similar Sample Images—0
Scale-Transferrable Object Detection—0
Enhancing the Spatial Resolution of Stereo Images Using a Parallax Prior—0
Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion CompensationCode0
A Papier-Mâché Approach to Learning 3D Surface Generation—0
Mesoscopic Facial Geometry Inference Using Deep Neural Networks—0
Show:102550
← PrevPage 355 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified