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 2001–2010 of 3874 papers

TitleStatusHype
Bayesian Based Unrolling for Reconstruction and Super-resolution of Single-Photon Lidar Systems—0
CycMuNet+: Cycle-Projected Mutual Learning for Spatial-Temporal Video Super-Resolution—0
Real-Time Neural Video Recovery and Enhancement on Mobile Devices—0
NLCUnet: Single-Image Super-Resolution Network with Hairline Details—0
PartDiff: Image Super-resolution with Partial Diffusion Models—0
Frequency-aware optical coherence tomography image super-resolution via conditional generative adversarial neural network—0
Real-time Inference and Extrapolation via a Diffusion-inspired Temporal Transformer Operator (DiTTO)—0
Soft-IntroVAE for Continuous Latent space Image Super-Resolution—0
A comparative analysis of SRGAN models—0
Surface Geometry Processing: An Efficient Normal-based Detail Representation—0
Show:102550
← PrevPage 201 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified