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 2021–2030 of 3874 papers

TitleStatusHype
Progressive Training of A Two-Stage Framework for Video RestorationCode1
A New Dataset and Transformer for Stereoscopic Video Super-ResolutionCode1
Deep Model-Based Super-Resolution with Non-uniform BlurCode1
FS-NCSR: Increasing Diversity of the Super-Resolution Space via Frequency Separation and Noise-Conditioned Normalizing FlowCode0
NTIRE 2022 Challenge on Stereo Image Super-Resolution: Methods and Results—0
NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and ResultsCode1
Learning Enriched Features for Fast Image Restoration and Enhancement—0
CTCNet: A CNN-Transformer Cooperation Network for Face Image Super-ResolutionCode1
Self-Calibrated Efficient Transformer for Lightweight Super-ResolutionCode1
Edge-enhanced Feature Distillation Network for Efficient Super-ResolutionCode1
Show:102550
← PrevPage 203 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified