SOTAVerified

Unified Image Restoration

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–17 of 17 papers

TitleStatusHype
CRNet: A Detail-Preserving Network for Unified Image Restoration and Enhancement TaskCode2
Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language ModelsCode4
Neural Degradation Representation Learning for All-In-One Image RestorationCode1
Controlling Vision-Language Models for Multi-Task Image RestorationCode2
Decomposition Ascribed Synergistic Learning for Unified Image Restoration—0
ProRes: Exploring Degradation-aware Visual Prompt for Universal Image RestorationCode1
Generative Diffusion Prior for Unified Image Restoration and Enhancement—0
Show:102550
← PrevPage 2 of 2Next →
All datasetsBSD68 sigma25GoProLOLRain100LRESIDE

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DA-RCOTAverage PSNR (dB)31.23—Unverified
#ModelMetricClaimedVerifiedStatus
1DA-RCOTAverage PSNR (dB)28.68—Unverified
#ModelMetricClaimedVerifiedStatus
1DA-RCOTAverage PSNR (dB)23.25—Unverified
#ModelMetricClaimedVerifiedStatus
1DA-RCOTAverage PSNR (dB)38.36—Unverified
#ModelMetricClaimedVerifiedStatus
1DA-RCOTAverage PSNR (dB)31.26—Unverified