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 621–630 of 3874 papers

TitleStatusHype
Image Super-resolution with An Enhanced Group Convolutional Neural NetworkCode1
SelfReformer: Self-Refined Network with Transformer for Salient Object DetectionCode1
Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video RestorationCode1
Residual Local Feature Network for Efficient Super-ResolutionCode1
Blueprint Separable Residual Network for Efficient Image Super-ResolutionCode1
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and ResultsCode1
MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-ResolutionCode1
Semi-Cycled Generative Adversarial Networks for Real-World Face Super-ResolutionCode1
Dual Adversarial Adaptation for Cross-Device Real-World Image Super-ResolutionCode1
DL4DS -- Deep Learning for empirical DownScalingCode1
Show:102550
← PrevPage 63 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified