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 3231–3240 of 3874 papers

TitleStatusHype
Optimal Transport driven CycleGAN for Unsupervised Learning in Inverse Problems—0
Analysis and Interpretation of Deep CNN Representations as Perceptual Quality Features—0
Pixel Co-Occurence Based Loss Metrics for Super Resolution Texture Recovery—0
Relative Pixel Prediction For Autoregressive Image Generation—0
Efficient Residual Dense Block Search for Image Super-ResolutionCode0
Deformable Non-local Network for Video Super-ResolutionCode0
Enhancing Traffic Scene Predictions with Generative Adversarial Networks—0
s-LWSR: Super Lightweight Super-Resolution NetworkCode0
DRCAS: Deep Restoration Network for Hardware Based Compressive Acquisition Scheme—0
Unsupervised Learning for Real-World Super-Resolution—0
Show:102550
← PrevPage 324 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified