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 1201–1210 of 3874 papers

TitleStatusHype
MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from FacesCode1
HDTR-Net: A Real-Time High-Definition Teeth Restoration Network for Arbitrary Talking Face Generation MethodsCode1
Deep Nonparametric Convexified Filtering for Computational Photography, Image Synthesis and Adversarial Defense—0
Deep Learning-based Synthetic High-Resolution In-Depth Imaging Using an Attachable Dual-element Endoscopic Ultrasound Probe—0
AudioSR: Versatile Audio Super-resolution at ScaleCode3
Learning from History: Task-agnostic Model Contrastive Learning for Image RestorationCode1
Padding-free Convolution based on Preservation of Differential Characteristics of Kernels—0
Introducing Shape Prior Module in Diffusion Model for Medical Image Segmentation—0
RGB-Guided Resolution Enhancement of IR Images—0
HAT: Hybrid Attention Transformer for Image RestorationCode3
Show:102550
← PrevPage 121 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified