SOTAVerified

Unified Image Restoration

Using a single model to restore inputs with different degradation types.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 17 papers

TitleStatusHype
LD-RPS: Zero-Shot Unified Image Restoration via Latent Diffusion Recurrent Posterior SamplingCode1
Boosting All-in-One Image Restoration via Self-Improved Privilege LearningCode1
Beyond Degradation Redundancy: Contrastive Prompt Learning for All-in-One Image RestorationCode1
UniCoRN: Latent Diffusion-based Unified Controllable Image Restoration Network across Multiple Degradations—0
Hybrid Agents for Image Restoration—0
UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Prior—0
Unified Image Restoration and Enhancement: Degradation Calibrated Cycle Reconstruction Diffusion ModelCode1
Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image RestorationCode3
UIR-LoRA: Achieving Universal Image Restoration through Multiple Low-Rank AdaptationCode0
Accurate Forgetting for All-in-One Image Restoration Model—0
Show:102550
← PrevPage 1 of 2Next →
All datasetsBSD68 sigma25GoProLOLRain100LRESIDE

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DA-RCOTAverage PSNR (dB)38.36—Unverified