SOTAVerified

Blind Super-Resolution

Blind Super-Resolution is an image processing technique that aims to reconstruct high-resolution images from low-resolution counterparts without prior knowledge of the degradation process.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 21–30 of 67 papers

TitleStatusHype
Flow-based Kernel Prior with Application to Blind Super-ResolutionCode1
Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded ImagesCode1
StarSRGAN: Improving Real-World Blind Super-ResolutionCode1
Degradation-Aware Self-Attention Based Transformer for Blind Image Super-ResolutionCode1
Knowledge Distillation based Degradation Estimation for Blind Super-ResolutionCode1
Dual-Diffusion: Dual Conditional Denoising Diffusion Probabilistic Models for Blind Super-Resolution Reconstruction in RSIsCode1
A-ESRGAN: Training Real-World Blind Super-Resolution with Attention U-Net DiscriminatorsCode1
End-to-end Alternating Optimization for Blind Super ResolutionCode1
End-to-end Alternating Optimization for Real-World Blind Super ResolutionCode1
The Best of Both Worlds: a Framework for Combining Degradation Prediction with High Performance Super-Resolution NetworksCode1
Show:102550
← PrevPage 3 of 7Next →

No leaderboard results yet.