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 1521–1530 of 3874 papers

TitleStatusHype
Perceptual-Distortion Balanced Image Super-Resolution is a Multi-Objective Optimization ProblemCode0
Enhancing digital core image resolution using optimal upscaling algorithm: with application to paired SEM images—0
aTENNuate: Optimized Real-time Speech Enhancement with Deep SSMs on Raw Audio—0
Solving Video Inverse Problems Using Image Diffusion Models—0
SeCo-INR: Semantically Conditioned Implicit Neural Representations for Improved Medical Image Super-Resolution—0
EarthGen: Generating the World from Top-Down ViewsCode0
Attention-Guided Multi-scale Interaction Network for Face Super-Resolution—0
DMRA: An Adaptive Line Spectrum Estimation Method through Dynamical Multi-Resolution of Atoms—0
HiTSR: A Hierarchical Transformer for Reference-based Super-ResolutionCode0
Beyond MR Image Harmonization: Resolution Matters Too—0
Show:102550
← PrevPage 153 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified