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 681–690 of 3874 papers

TitleStatusHype
Diffusion Models Beat GANs on Image ClassificationCode1
High-dimensional Dense Residual Convolutional Neural Network for Light Field ReconstructionCode1
Diffusion Model Based Posterior Sampling for Noisy Linear Inverse ProblemsCode1
DiffFuSR: Super-Resolution of all Sentinel-2 Multispectral Bands using Diffusion ModelsCode1
High-Resolution Image Editing via Multi-Stage Blended DiffusionCode1
Diffusion-based Blind Text Image Super-ResolutionCode1
CVAE-GAN: Fine-Grained Image Generation through Asymmetric TrainingCode1
HQ-50K: A Large-scale, High-quality Dataset for Image RestorationCode1
DiSR-NeRF: Diffusion-Guided View-Consistent Super-Resolution NeRFCode1
Detail-Preserving Transformer for Light Field Image Super-ResolutionCode1
Show:102550
← PrevPage 69 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified