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 2391–2400 of 3874 papers

TitleStatusHype
Improved Super Resolution of MR Images Using CNNs and Vision Transformers—0
Calcium oscillation on homogeneous and heterogeneous networks of ryanodine receptor—0
Semantic uncertainty intervals for disentangled latent spacesCode0
Efficient Meta-Tuning for Content-aware Neural Video DeliveryCode0
Flow-based Visual Quality Enhancer for Super-resolution Magnetic Resonance Spectroscopic ImagingCode0
HSE-NN Team at the 4th ABAW Competition: Multi-task Emotion Recognition and Learning from Synthetic Images—0
Geometry-Aware Reference Synthesis for Multi-View Image Super-Resolution—0
Learning Knowledge Representation with Meta Knowledge Distillation for Single Image Super-Resolution—0
Stochastic Attribute Modeling for Face Super-Resolution—0
Untrained, physics-informed neural networks for structured illumination microscopy—0
Show:102550
← PrevPage 240 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified