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 901–950 of 1459 papers

TitleStatusHype
Fast and High-Quality Image Denoising via Malleable Convolutions—0
Learning Self-prior for Mesh Denoising using Dual Graph Convolutional NetworksCode1
XYDeblur: Divide and Conquer for Single Image DeblurringCode1
GIQE: Generic Image Quality Enhancement via Nth Order Iterative Degradation—0
KNN Local Attention for Image Restoration—0
All-in-One Image Restoration for Unknown CorruptionCode2
Self-Supervised Deep Image Restoration via Adaptive Stochastic Gradient Langevin DynamicsCode1
Image Restoration using Feature-guidance—0
A Trained Regularization Approach Based on Born Iterative Method for Electromagnetic Imaging—0
On Asymptotic Linear Convergence of Projected Gradient Descent for Constrained Least Squares—0
Procedural Kernel Networks—0
SiamTrans: Zero-Shot Multi-Frame Image Restoration with Pre-Trained Siamese Transformers—0
Kernel-aware Burst Blind Super-ResolutionCode0
Improving Image Restoration by Revisiting Global Information AggregationCode2
U2-Former: A Nested U-shaped Transformer for Image Restoration—0
Unsupervised Low-Light Image Enhancement via Histogram Equalization PriorCode1
SAR Image Despeckling Using Continuous Attention ModuleCode1
Deep Self-Dissimilarities as Powerful Visual Fingerprints—0
Event-Based Fusion for Motion Deblurring with Cross-modal AttentionCode1
TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather ConditionsCode1
Performance of a GPU- and Time-Efficient Pseudo 3D Network for Magnetic Resonance Image Super-Resolution and Motion Artifact Reduction—0
A Practical Contrastive Learning Framework for Single-Image Super-ResolutionCode1
ISNAS-DIP: Image-Specific Neural Architecture Search for Deep Image PriorCode1
Learning Discriminative Shrinkage Deep Networks for Image DeconvolutionCode0
A Novel Framework for Image-to-image Translation and Image Compression—0
A Close Look at Few-shot Real Image Super-resolution from the Distortion Relation Perspective—0
An Educated Warm Start For Deep Image Prior-Based Micro CT ReconstructionCode0
A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image RestorationCode1
Restormer: Efficient Transformer for High-Resolution Image RestorationCode1
SAPNet: Segmentation-Aware Progressive Network for Perceptual Contrastive DerainingCode1
Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image ReconstructionCode3
A Study on the Efficient Product Search Service for the Damaged Image Information—0
FINO: Flow-based Joint Image and Noise Model—0
ISP-Agnostic Image Reconstruction for Under-Display Cameras—0
Functional Neural Networks for Parametric Image Restoration Problems—0
Unsupervised PET Reconstruction from a Bayesian Perspective—0
An Effective Image Restorer: Denoising and Luminance Adjustment for Low-photon-count Imaging—0
Improving Super-Resolution Performance using Meta-Attention LayersCode1
Learning Continuous Face Representation with Explicit Functions—0
As if by magic: self-supervised training of deep despeckling networks with MERLINCode1
Unsupervised Image Fusion Using Deep Image Priors—0
Towards General Deep Leakage in Federated LearningCode0
Identity-guided Face Generation with Multi-modal Contour Conditions—0
Burst Image Restoration and EnhancementCode1
Generative Modeling with Optimal Transport MapsCode1
Fast Scalable Image Restoration using Total Variation Priors and Expectation Propagation—0
Preconditioned Plug-and-Play ADMM with Locally Adjustable Denoiser for Image Restoration—0
Residual Contrastive Learning: Unsupervised Representation Learning from Residuals—0
Lottery Image Prior—0
Towards Flexible Blind JPEG Artifacts RemovalCode1
Show:102550
← PrevPage 19 of 30Next →
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