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
MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral ReconstructionCode5
MambaIRv2: Attentive State Space RestorationCode5
DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset CurationCode5
Efficient Diffusion Model for Image Restoration by Residual ShiftingCode5
GLEAN: Generative Latent Bank for Image Super-Resolution and BeyondCode5
MambaIR: A Simple Baseline for Image Restoration with State-Space ModelCode5
Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image RestorationCode4
DocRes: A Generalist Model Toward Unifying Document Image Restoration TasksCode4
Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language ModelsCode4
A Survey on Visual MambaCode4
Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian NoiseCode4
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space ModelCode4
Simple Baselines for Image RestorationCode4
InstructIR: High-Quality Image Restoration Following Human InstructionsCode4
DiffBIR: Towards Blind Image Restoration with Generative Diffusion PriorCode4
NAFSSR: Stereo Image Super-Resolution Using NAFNetCode4
One-Step Effective Diffusion Network for Real-World Image Super-ResolutionCode4
A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future TrendsCode3
FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image RestorationCode3
VRT: A Video Restoration TransformerCode3
SwinIR: Image Restoration Using Swin TransformerCode3
VmambaIR: Visual State Space Model for Image RestorationCode3
TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-ResolutionCode3
Unlimited-Size Diffusion RestorationCode3
Restoring Images in Adverse Weather Conditions via Histogram TransformerCode3
Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image RestorationCode3
Self-Rectifying Diffusion Sampling with Perturbed-Attention GuidanceCode3
Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized StylizationCode3
OneRestore: A Universal Restoration Framework for Composite DegradationCode3
AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and ModulationCode3
Old Photo Restoration via Deep Latent Space TranslationCode3
PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language InstructionsCode3
MAXIM: Multi-Axis MLP for Image ProcessingCode3
Cold Diffusion: Inverting Arbitrary Image Transforms Without NoiseCode3
Instruct-IPT: All-in-One Image Processing Transformer via Weight ModulationCode3
HAT: Hybrid Attention Transformer for Image RestorationCode3
Blind Image Restoration via Fast Diffusion InversionCode3
Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image ReconstructionCode3
Bringing Old Photos Back to LifeCode3
Single-Image Shadow Removal Using Deep Learning: A Comprehensive SurveyCode3
DarkIR: Robust Low-Light Image RestorationCode3
Efficient Frequency Domain-based Transformers for High-Quality Image DeblurringCode2
BaryIR: Learning Multi-Source Unified Representation in Continuous Barycenter Space for Generalizable All-in-One Image RestorationCode2
Efficient Visual State Space Model for Image DeblurringCode2
Efficient and Explicit Modelling of Image Hierarchies for Image RestorationCode2
EAMamba: Efficient All-Around Vision State Space Model 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
Dual-domain strip attention for image restorationCode2
Diffusion Models for Image Restoration and Enhancement -- A Comprehensive SurveyCode2
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