SOTAVerified

Image Restoration

Image Restoration is a family of inverse problems for obtaining a high quality image from a corrupted input image. Corruption may occur due to the image-capture process (e.g., noise, lens blur), post-processing (e.g., JPEG compression), or photography in non-ideal conditions (e.g., haze, motion blur).

Source: Blind Image Restoration without Prior Knowledge

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 951–960 of 1459 papers

TitleStatusHype
CurvPnP: Plug-and-play Blind Image Restoration with Deep Curvature DenoiserCode0
DriftRec: Adapting diffusion models to blind JPEG restorationCode0
ClassPruning: Speed Up Image Restoration Networks by Dynamic N:M Pruning—0
Perceptual Image Enhancement for Smartphone Real-Time Applications—0
DiffGAR: Model-Agnostic Restoration from Generative Artifacts Using Image-to-Image Diffusion Models—0
Hand Gestures Recognition in Videos Taken with Lensless Camera—0
Guided Nonlocal Patch Regularization and Efficient Filtering-Based Inversion for Multiband Fusion—0
Low-Light Image Restoration Based on Retina Model using Neural Networks—0
Dual-former: Hybrid Self-attention Transformer for Efficient Image Restoration—0
R2C-GAN: Restore-to-Classify Generative Adversarial Networks for Blind X-Ray Restoration and COVID-19 ClassificationCode0
Show:102550
← PrevPage 96 of 146Next →
All datasetsCDD-11UHDM.

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1OneRestoreAverage PSNR (dB)28.72—Unverified
2SRUDCAverage PSNR (dB)27.64—Unverified
3RestormerAverage PSNR (dB)26.99—Unverified
4WGWSNetAverage PSNR (dB)26.96—Unverified
5DGUNetAverage PSNR (dB)26.92—Unverified
6OKNetAverage PSNR (dB)26.33—Unverified
7MIRNetAverage PSNR (dB)25.97—Unverified
8PromptIRAverage PSNR (dB)25.9—Unverified
9MPRNetAverage PSNR (dB)25.47—Unverified
10MIRNetv2Average PSNR (dB)25.37—Unverified
#ModelMetricClaimedVerifiedStatus
1ESDNet-LPSNR22.42—Unverified
2ESDNetPSNR22.12—Unverified
#ModelMetricClaimedVerifiedStatus
1730L37—Unverified