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 2331–2340 of 3874 papers

TitleStatusHype
Hierarchical Neural Operator Transformer with Learnable Frequency-aware Loss Prior for Arbitrary-scale Super-resolution—0
Hierarchical Similarity Learning for Aliasing Suppression Image Super-Resolution—0
Hierarchy-Aware and Channel-Adaptive Semantic Communication for Bandwidth-Limited Data Fusion—0
High Dynamic Range and Super-Resolution from Raw Image Bursts—0
Higher-order MRFs based image super resolution: why not MAP?—0
High-Frequency aware Perceptual Image Enhancement—0
HIGHLY EFFICIENT 8-BIT LOW PRECISION INFERENCE OF CONVOLUTIONAL NEURAL NETWORKS—0
High Quality Remote Sensing Image Super-Resolution Using Deep Memory Connected Network—0
High-quality Speech Synthesis Using Super-resolution Mel-Spectrogram—0
High Resolution 3D Shape Texture from Multiple Videos—0
Show:102550
← PrevPage 234 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified