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 851–860 of 3874 papers

TitleStatusHype
Deep Reparametrization of Multi-Frame Super-Resolution and DenoisingCode1
Reference-based Image Super-Resolution with Deformable Attention TransformerCode1
BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural NetworksCode1
BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable AlignmentCode1
Deep Learning-Driven Ultra-High-Definition Image Restoration: A SurveyCode1
DeepSEE: Deep Disentangled Semantic Explorative Extreme Super-ResolutionCode1
Image-specific Convolutional Kernel Modulation for Single Image Super-resolutionCode1
ReLUs Are Sufficient for Learning Implicit Neural RepresentationsCode1
Deep Learning for Efficient Reconstruction of High-Resolution Turbulent DNS DataCode1
Learning Deep Interleaved Networks with Asymmetric Co-Attention for Image RestorationCode1
Show:102550
← PrevPage 86 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified