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 301–350 of 1459 papers

TitleStatusHype
Basic Binary Convolution Unit for Binarized Image Restoration NetworkCode1
Early Exit or Not: Resource-Efficient Blind Quality Enhancement for Compressed ImagesCode1
Bayesian Image Reconstruction using Deep Generative ModelsCode1
MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image InpaintingCode1
MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image RecoveryCode1
Decoupled Data Consistency with Diffusion Purification for Image RestorationCode1
MMV_Im2Im: An Open Source Microscopy Machine Vision Toolbox for Image-to-Image TransformationCode1
End-to-End Learning for Joint Image Demosaicing, Denoising and Super-ResolutionCode1
Decoupling Degradations with Recurrent Network for Video Restoration in Under-Display CameraCode1
Deep Atrous Guided Filter for Image Restoration in Under Display CamerasCode1
Diffusion State-Guided Projected Gradient for Inverse ProblemsCode1
DaLPSR: Leverage Degradation-Aligned Language Prompt for Real-World Image Super-ResolutionCode1
Memory-Efficient Hierarchical Neural Architecture Search for Image RestorationCode1
Enhancing Intrinsic Adversarial Robustness via Feature Pyramid DecoderCode1
Diffusion Priors for Variational Likelihood Estimation and Image DenoisingCode1
D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image RestorationCode1
EnlightenGAN: Deep Light Enhancement without Paired SupervisionCode1
Enlighten Anything: When Segment Anything Model Meets Low-Light Image EnhancementCode1
Memory augment is All You Need for image restorationCode1
MetaWeather: Few-Shot Weather-Degraded Image RestorationCode1
Beyond Degradation Conditions: All-in-One Image Restoration via HOG TransformersCode1
Exploiting Raw Images for Real-Scene Super-ResolutionCode1
Beyond Degradation Redundancy: Contrastive Prompt Learning for All-in-One Image RestorationCode1
Deep Image PriorCode1
Neural Degradation Representation Learning for All-In-One Image RestorationCode1
Deep Image Semantic Communication Model for Artificial Intelligent Internet of ThingsCode1
CycleISP: Real Image Restoration via Improved Data SynthesisCode1
AutoDIR: Automatic All-in-One Image Restoration with Latent DiffusionCode1
BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image RestorationCode1
Exploring the potential of channel interactions for image restorationCode1
Diffusion Posterior Proximal Sampling for Image RestorationCode1
Annular Computational Imaging: Capture Clear Panoramic Images through Simple LensCode1
Bitstream-Corrupted JPEG Images are Restorable: Two-stage Compensation and Alignment Framework for Image RestorationCode1
Deep Linear Array Pushbroom Image Restoration: A Degradation Pipeline and Jitter-Aware Restoration NetworkCode1
Event-Based Fusion for Motion Deblurring with Cross-modal AttentionCode1
MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-ResolutionCode1
BlindDiff: Empowering Degradation Modelling in Diffusion Models for Blind Image Super-ResolutionCode1
A Universal Scale-Adaptive Deformable Transformer for Image Restoration across Diverse ArtifactsCode1
Flare-Free Vision: Empowering Uformer with Depth InsightsCode1
Deep Optimal Transport: A Practical Algorithm for Photo-realistic Image RestorationCode1
MatIR: A Hybrid Mamba-Transformer Image Restoration ModelCode1
Deep Plug-and-Play Super-Resolution for Arbitrary Blur KernelsCode1
Ab-initio Contrast Estimation and Denoising of Cryo-EM ImagesCode1
Cross-Scale Internal Graph Neural Network for Image Super-ResolutionCode1
Deep Reparametrization of Multi-Frame Super-Resolution and DenoisingCode1
From Rank Estimation to Rank Approximation: Rank Residual Constraint for Image RestorationCode1
Blind Inverse Gamma Correction with Maximized Differential EntropyCode1
Deep Semantic Statistics Matching (D2SM) Denoising NetworkCode1
Cross Aggregation Transformer for Image RestorationCode1
Attentive Fine-Grained Structured Sparsity for Image RestorationCode1
Show:102550
← PrevPage 7 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