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 451–475 of 1459 papers

TitleStatusHype
High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented TransformerCode1
Adaptive Cross-Layer Attention for Image RestorationCode1
Generating Aligned Pseudo-Supervision from Non-Aligned Data for Image Restoration in Under-Display CameraCode1
Generative Modeling with Optimal Transport MapsCode1
A Comparative Study of Image Restoration Networks for General Backbone Network DesignCode1
Towards Real-World Adverse Weather Image Restoration: Enhancing Clearness and Semantics with Vision-Language ModelsCode1
Generalizable Medical Image Segmentation via Random Amplitude Mixup and Domain-Specific Image RestorationCode1
GenISP: Neural ISP for Low-Light Machine CognitionCode1
FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly DetectionCode1
A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image RestorationCode1
Uformer: A General U-Shaped Transformer for Image RestorationCode1
UHD-processer: Unified UHD Image Restoration with Progressive Frequency Learning and Degradation-aware PromptsCode1
From Rank Estimation to Rank Approximation: Rank Residual Constraint for Image RestorationCode1
Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models trained on Corrupted DataCode1
Compound Multi-branch Feature Fusion for Real Image RestorationCode1
Underwater Image Restoration via Polymorphic Large Kernel CNNsCode1
Enhancing RAW-to-sRGB with Decoupled Style Structure in Fourier DomainCode1
From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral PerspectiveCode1
Improving Super-Resolution Performance using Meta-Attention LayersCode1
End-to-End Learning for Joint Image Demosaicing, Denoising and Super-ResolutionCode1
Masked Frequency Modeling for Self-Supervised Visual Pre-TrainingCode1
Freqformer: Image-Demoiréing Transformer via Efficient Frequency DecompositionCode1
Controllable Image Restoration for Under-Display Camera in Smartphones—0
A Theory of the Distortion-Perception Tradeoff in Wasserstein Space—0
Alternative design of DeepPDNet in the context of image restoration—0
Show:102550
← PrevPage 19 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