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 3071–3080 of 3874 papers

TitleStatusHype
Adaptive Loss Function for Super Resolution Neural Networks Using Convex Optimization Techniques—0
ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial NetworkCode1
Multimodal Deep Unfolding for Guided Image Super-Resolution—0
Sinogram super-resolution and denoising convolutional neural network (SRCN) for limited data photoacoustic tomography—0
DeepSUM++: Non-local Deep Neural Network for Super-Resolution of Unregistered Multitemporal Images—0
Spatial-Spectral Residual Network for Hyperspectral Image Super-Resolution—0
Learned Multi-View Texture Super-Resolution—0
Neural Architecture Search for Deep Image PriorCode0
Segmentation and Generation of Magnetic Resonance Images by Deep Neural NetworksCode0
Fast Adaptation to Super-Resolution Networks via Meta-LearningCode1
Show:102550
← PrevPage 308 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified