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 1841–1850 of 3874 papers

TitleStatusHype
Hundred-Kilobyte Lookup Tables for Efficient Single-Image Super-ResolutionCode0
Precipitation Downscaling with Spatiotemporal Video Diffusion—0
Transformer-based Selective Super-Resolution for Efficient Image RefinementCode0
AniRes2D: Anisotropic Residual-enhanced Diffusion for 2D MR Super-Resolution—0
Generative Powers of Ten—0
SRTransGAN: Image Super-Resolution using Transformer based Generative Adversarial Network—0
TMSR: Tiny Multi-path CNNs for Super Resolution—0
J-Net: Improved U-Net for Terahertz Image Super-Resolution—0
ESTformer: Transformer Utilizing Spatiotemporal Dependencies for Electroencaphalogram Super-resolution—0
Spectral-wise Implicit Neural Representation for Hyperspectral Image Reconstruction—0
Show:102550
← PrevPage 185 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified