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 591–600 of 3874 papers

TitleStatusHype
HAZE-Net: High-Frequency Attentive Super-Resolved Gaze Estimation in Low-Resolution Face ImagesCode1
Cross-Scale Internal Graph Neural Network for Image Super-ResolutionCode1
Cascaded Local Implicit Transformer for Arbitrary-Scale Super-ResolutionCode1
ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data CharacteristicCode1
3D Human Pose, Shape and Texture from Low-Resolution Images and VideosCode1
ControlSR: Taming Diffusion Models for Consistent Real-World Image Super ResolutionCode1
Deep Blind Super-Resolution for Satellite VideoCode1
Deep Blind Video Super-resolutionCode1
CTCNet: A CNN-Transformer Cooperation Network for Face Image Super-ResolutionCode1
GenerateCT: Text-Conditional Generation of 3D Chest CT VolumesCode1
Show:102550
← PrevPage 60 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified