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 3381–3390 of 3874 papers

TitleStatusHype
Progressive Generative Adversarial Networks for Medical Image Super resolution—0
DFuseNet: Deep Fusion of RGB and Sparse Depth Information for Image Guided Dense Depth CompletionCode0
Deep Hyperspectral Prior: Denoising, Inpainting, Super-ResolutionCode0
Compressing GANs using Knowledge Distillation—0
Deep Learning for Inverse Problems: Bounds and Regularizers—0
Medical Image Super-Resolution Using a Generative Adversarial Network—0
Resolution enhancement in scanning electron microscopy using deep learning—0
TGAN: Deep Tensor Generative Adversarial Nets for Large Image GenerationCode0
Fast, Accurate and Lightweight Super-Resolution with Neural Architecture SearchCode0
Adversarial training with cycle consistency for unsupervised super-resolution in endomicroscopy—0
Show:102550
← PrevPage 339 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified