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 726–750 of 1459 papers

TitleStatusHype
Sharing Key Semantics in Transformer Makes Efficient Image RestorationCode0
Fast Samplers for Inverse Problems in Iterative Refinement ModelsCode0
Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Models—0
Hierarchical Uncertainty Exploration via Feedforward Posterior Trees—0
Blaze3DM: Marry Triplane Representation with Diffusion for 3D Medical Inverse Problem Solving—0
Efficient Degradation-aware Any Image Restoration—0
Perceptual Fairness in Image Restoration—0
DARK: Denoising, Amplification, Restoration KitCode0
A New Cross-Space Total Variation Regularization Model for Color Image Restoration with Quaternion Blur Operator—0
Emphasizing Crucial Features for Efficient Image RestorationCode0
A Versatile Framework for Analyzing Galaxy Image Data by Implanting Human-in-the-loop on a Large Vision Model—0
RSDehamba: Lightweight Vision Mamba for Remote Sensing Satellite Image Dehazing—0
NTIRE 2024 Restore Any Image Model (RAIM) in the Wild Challenge—0
FRRffusion: Unveiling Authenticity with Diffusion-Based Face Retouching ReversalCode0
Deep Image Restoration For Image Anti-ForensicsCode0
Reconstructing Satellites in 3D from Amateur Telescope Images—0
One-Shot Image Restoration—0
NTIRE 2024 Quality Assessment of AI-Generated Content Challenge—0
Face2Face: Label-driven Facial Retouching Restoration—0
CU-Mamba: Selective State Space Models with Channel Learning for Image Restoration—0
AdaIR: Exploiting Underlying Similarities of Image Restoration Tasks with Adapters—0
OmniSSR: Zero-shot Omnidirectional Image Super-Resolution using Stable Diffusion Model—0
Improving Bracket Image Restoration and Enhancement with Flow-guided Alignment and Enhanced Feature Aggregation—0
Joint Conditional Diffusion Model for Image Restoration with Mixed Degradations—0
Single Stage Adaptive Multi-Attention Network for Image RestorationCode0
Show:102550
← PrevPage 30 of 59Next →
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