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 3471–3480 of 3874 papers

TitleStatusHype
Learning for Video Super-Resolution through HR Optical Flow EstimationCode1
Image Denoising and Super-Resolution using Residual Learning of Deep Convolutional Network—0
The 2018 PIRM Challenge on Perceptual Image Super-resolutionCode1
Dual Reconstruction Nets for Image Super-Resolution with Gradient Sensitive Loss—0
Image Super-Resolution via Deterministic-Stochastic Synthesis and Local Statistical RectificationCode0
Toward Bridging the Simulated-to-Real Gap: Benchmarking Super-Resolution on Real Data—0
Generative adversarial network-based image super-resolution using perceptual content lossesCode0
Deep Learning-based Image Super-Resolution Considering Quantitative and Perceptual QualityCode0
Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolution—0
Deep MR Image Super-Resolution Using Structural Priors—0
Show:102550
← PrevPage 348 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified