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 1621–1630 of 3874 papers

TitleStatusHype
Multi-Scale Feature Fusion using Channel Transformers for Guided Thermal Image Super Resolution—0
LFMamba: Light Field Image Super-Resolution with State Space Model—0
A Dictionary Based Approach for Removing Out-of-Focus BlurCode0
Geometric Distortion Guided Transformer for Omnidirectional Image Super-Resolution—0
Bayesian Conditioned Diffusion Models for Inverse Problems—0
GaussianSR: 3D Gaussian Super-Resolution with 2D Diffusion Priors—0
SatDiffMoE: A Mixture of Estimation Method for Satellite Image Super-resolution with Latent Diffusion Models—0
DDR: Exploiting Deep Degradation Response as Flexible Image DescriptorCode0
Towards Realistic Data Generation for Real-World Super-Resolution—0
Image Neural Field Diffusion Models—0
Show:102550
← PrevPage 163 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified