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

Showing 801810 of 3874 papers

TitleStatusHype
DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional FlowsCode1
Deep Blind Super-Resolution for Satellite VideoCode1
Deep Blind Video Super-resolutionCode1
MoTIF: Learning Motion Trajectories with Local Implicit Neural Functions for Continuous Space-Time Video Super-ResolutionCode1
Deep Burst Super-ResolutionCode1
LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion ModelCode1
BurstM: Deep Burst Multi-scale SR using Fourier Space with Optical FlowCode1
Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark EstimationCode1
DREAM: Diffusion Rectification and Estimation-Adaptive ModelsCode1
DSR: Towards Drone Image Super-ResolutionCode1
Show:102550
← PrevPage 81 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41Unverified