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 1–50 of 1459 papers

TitleStatusHype
MambaIR: A Simple Baseline for Image Restoration with State-Space ModelCode5
DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset CurationCode5
GLEAN: Generative Latent Bank for Image Super-Resolution and BeyondCode5
Efficient Diffusion Model for Image Restoration by Residual ShiftingCode5
MambaIRv2: Attentive State Space RestorationCode5
MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral ReconstructionCode5
Simple Baselines for Image RestorationCode4
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space ModelCode4
DocRes: A Generalist Model Toward Unifying Document Image Restoration TasksCode4
A Survey on Visual MambaCode4
Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image RestorationCode4
DiffBIR: Towards Blind Image Restoration with Generative Diffusion PriorCode4
Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language ModelsCode4
InstructIR: High-Quality Image Restoration Following Human InstructionsCode4
Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian NoiseCode4
One-Step Effective Diffusion Network for Real-World Image Super-ResolutionCode4
NAFSSR: Stereo Image Super-Resolution Using NAFNetCode4
Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image RestorationCode3
FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image RestorationCode3
Self-Rectifying Diffusion Sampling with Perturbed-Attention GuidanceCode3
A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future TrendsCode3
Unlimited-Size Diffusion RestorationCode3
VRT: A Video Restoration TransformerCode3
VmambaIR: Visual State Space Model for Image RestorationCode3
Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized StylizationCode3
AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and ModulationCode3
Restoring Images in Adverse Weather Conditions via Histogram TransformerCode3
Single-Image Shadow Removal Using Deep Learning: A Comprehensive SurveyCode3
PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language InstructionsCode3
OneRestore: A Universal Restoration Framework for Composite DegradationCode3
SwinIR: Image Restoration Using Swin TransformerCode3
Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image ReconstructionCode3
Cold Diffusion: Inverting Arbitrary Image Transforms Without NoiseCode3
HAT: Hybrid Attention Transformer for Image RestorationCode3
Bringing Old Photos Back to LifeCode3
Blind Image Restoration via Fast Diffusion InversionCode3
Instruct-IPT: All-in-One Image Processing Transformer via Weight ModulationCode3
MAXIM: Multi-Axis MLP for Image ProcessingCode3
Old Photo Restoration via Deep Latent Space TranslationCode3
TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-ResolutionCode3
DarkIR: Robust Low-Light Image RestorationCode3
Efficient Frequency Domain-based Transformers for High-Quality Image DeblurringCode2
Efficient Visual State Space Model for Image DeblurringCode2
EAMamba: Efficient All-Around Vision State Space Model for Image RestorationCode2
Dynamic Pre-training: Towards Efficient and Scalable All-in-One Image RestorationCode2
Efficient and Explicit Modelling of Image Hierarchies for Image RestorationCode2
EnsIR: An Ensemble Algorithm for Image Restoration via Gaussian Mixture ModelsCode2
DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and Landmark-Guided TransformerCode2
Diffusion Models for Image Restoration and Enhancement -- A Comprehensive SurveyCode2
A Survey of Deep Face Restoration: Denoise, Super-Resolution, Deblur, Artifact RemovalCode2
Show:102550
← PrevPage 1 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