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 3241–3250 of 3874 papers

TitleStatusHype
SRMAE: Masked Image Modeling for Scale-Invariant Deep Representations—0
SR-NeRV: Improving Embedding Efficiency of Neural Video Representation via Super-Resolution—0
SRNR: Training neural networks for Super-Resolution MRI using Noisy high-resolution Reference data—0
SRN-SZ: Deep Leaning-Based Scientific Error-bounded Lossy Compression with Super-resolution Neural Networks—0
SROBB: Targeted Perceptual Loss for Single Image Super-Resolution—0
SRPGAN: Perceptual Generative Adversarial Network for Single Image Super Resolution—0
SRR-Net: A Super-Resolution-Involved Reconstruction Method for High Resolution MR Imaging—0
SRTGAN: Triplet Loss based Generative Adversarial Network for Real-World Super-Resolution—0
SRTransGAN: Image Super-Resolution using Transformer based Generative Adversarial Network—0
A Low-Resolution Image is Worth 1x1 Words: Enabling Fine Image Super-Resolution with Transformers and TaylorShift—0
Show:102550
← PrevPage 325 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified