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 3431–3440 of 3874 papers

TitleStatusHype
Joint Face Hallucination and Deblurring via Structure Generation and Detail Enhancement—0
Three-dimensional Optical Coherence Tomography Image Denoising through Multi-input Fully-Convolutional Networks—0
Low-Resolution Face Recognition—0
Deep Unfolded Robust PCA with Application to Clutter Suppression in Ultrasound—0
Adversarial Feedback LoopCode0
Learning to synthesize: splitting and recombining low and high spatial frequencies for image recovery—0
Single Snapshot Super-Resolution DOA Estimation for Arbitrary Array Geometries—0
A Learning-Based Framework for Line-Spectra Super-resolutionCode0
LookinGood: Enhancing Performance Capture with Real-time Neural Re-Rendering—0
Blockwise Parallel Decoding for Deep Autoregressive ModelsCode1
Show:102550
← PrevPage 344 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified