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 551–575 of 1459 papers

TitleStatusHype
Unifying Image Processing as Visual Prompting Question Answering—0
AutoDIR: Automatic All-in-One Image Restoration with Latent DiffusionCode1
Frequency-Aware Re-Parameterization for Over-Fitting Based Image Compression—0
Degradation-Aware Self-Attention Based Transformer for Blind Image Super-ResolutionCode1
Deformation-Invariant Neural Network and Its Applications in Distorted Image Restoration and Analysis—0
Leveraging Classic Deconvolution and Feature Extraction in Zero-Shot Image RestorationCode0
A Restoration Network as an Implicit Prior—0
JPEG Information Regularized Deep Image Prior for Denoising—0
Controlling Vision-Language Models for Multi-Task Image RestorationCode2
Guided Frequency Loss for Image Restoration—0
Uncertainty Quantification via Neural Posterior Principal Components—0
Survey on Deep Face Restoration: From Non-blind to Blind and BeyondCode1
On the Posterior Distribution in Denoising: Application to Uncertainty QuantificationCode1
Training Your Image Restoration Network Better with Random Weight Network as Optimization Function—0
Training Your Image Restoration Network Better with Random Weight Network as Optimization Function—0
Deshadow-Anything: When Segment Anything Model Meets Zero-shot shadow removal—0
License Plate Super-Resolution Using Diffusion Models—0
Reconstruct-and-Generate Diffusion Model for Detail-Preserving Image Denoising—0
AOSR-Net: All-in-One Sandstorm Removal Network—0
A Multi-scale Generalized Shrinkage Threshold Network for Image Blind Deblurring in Remote Sensing—0
FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly DetectionCode1
Learning from History: Task-agnostic Model Contrastive Learning for Image RestorationCode1
HAT: Hybrid Attention Transformer for Image RestorationCode3
Prompt-based Ingredient-Oriented All-in-One Image RestorationCode1
Advanced Underwater Image Restoration in Complex Illumination Conditions—0
Show:102550
← PrevPage 23 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