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 121–130 of 3874 papers

TitleStatusHype
Blur Interpolation Transformer for Real-World Motion from BlurCode2
Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-ResolutionCode2
DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration ModelsCode2
Misalignment-Robust Frequency Distribution Loss for Image TransformationCode2
AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion DistillationCode2
Denoising Diffusion Models for Plug-and-Play Image RestorationCode2
Denoising Diffusion Restoration ModelsCode2
Diffusion Models for Image Restoration and Enhancement -- A Comprehensive SurveyCode2
All-In-One Medical Image Restoration via Task-Adaptive RoutingCode2
Deep Constrained Least Squares for Blind Image Super-ResolutionCode2
Show:102550
← PrevPage 13 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified