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 3631–3640 of 3874 papers

TitleStatusHype
Accelerating GMM-based patch priors for image restoration: Three ingredients for a 100 speed-up—0
Generative Adversarial Networks: An OverviewCode0
Retinal Vasculature Segmentation Using Local Saliency Maps and Generative Adversarial Networks For Image Super Resolution—0
A Review of Convolutional Neural Networks for Inverse Problems in ImagingCode0
UG^2: a Video Benchmark for Assessing the Impact of Image Restoration and Enhancement on Automatic Visual Recognition—0
Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid NetworksCode0
Blind Image Fusion for Hyperspectral Imaging with the Directional Total VariationCode0
Temporal shape super-resolution by intra-frame motion encoding using high-fps structured light—0
Anchored Regression Networks Applied to Age Estimation and Super Resolution—0
Supplementary Meta-Learning: Towards a Dynamic Model for Deep Neural Networks—0
Show:102550
← PrevPage 364 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified