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 3131–3140 of 3874 papers

TitleStatusHype
Learning to Zoom-in via Learning to Zoom-out: Real-world Super-resolution by Generating and Adapting Degradation—0
Improving Few-shot Learning by Spatially-aware Matching and CrossTransformer—0
Hyperspectral Super-Resolution via Coupled Tensor Ring Factorization—0
End-To-End Trainable Video Super-Resolution Based on a New Mechanism for Implicit Motion Estimation and Compensation—0
Enforcing Physical Constraints in Neural Neural Networks through Differentiable PDE LayerCode0
VideoOneNet: Bidirectional Convolutional Recurrent OneNet with Trainable Data Steps for Video ProcessingCode0
LOSSLESS SINGLE IMAGE SUPER RESOLUTION FROM LOW-QUALITY JPG IMAGES—0
Multi-modality super-resolution loss for GAN-based super-resolution of clinical CT images using micro CT image database—0
Characteristic Regularisation for Super-Resolving Face Images—0
Self-supervised Fine-tuning for Correcting Super-Resolution Convolutional Neural Networks—0
Show:102550
← PrevPage 314 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified