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 801–850 of 1459 papers

TitleStatusHype
Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion ModelsCode2
GLEAN: Generative Latent Bank for Image Super-Resolution and BeyondCode5
DnSwin: Toward Real-World Denoising via Continuous Wavelet Sliding-TransformerCode1
Real Image Restoration via Structure-preserving Complementarity Attention—0
REPNP: Plug-and-Play with Deep Reinforcement Learning Prior for Robust Image Restoration—0
Enhancing Image Rescaling using Dual Latent Variables in Invertible Neural NetworkCode0
Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects SuppressionCode2
DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided NetworkCode2
A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and RestorationCode1
Towards Efficient and Scale-Robust Ultra-High-Definition Image DemoireingCode2
Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer ModelCode1
Deep Semantic Statistics Matching (D2SM) Denoising NetworkCode1
Global-Local Stepwise Generative Network for Ultra High-Resolution Image RestorationCode0
RCRN: Real-world Character Image Restoration Network via Skeleton ExtractionCode0
Structural Prior Guided Generative Adversarial Transformers for Low-Light Image Enhancement—0
Tilt-then-Blur or Blur-then-Tilt? Clarifying the Atmospheric Turbulence Model—0
MSP-Former: Multi-Scale Projection Transformer for Single Image Desnowing—0
Denoising single images by feature ensemble revisited—0
Snow Mask Guided Adaptive Residual Network for Image Snow Removal—0
D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image RestorationCode1
DRL-ISP: Multi-Objective Camera ISP with Deep Reinforcement Learning—0
Degradation-Guided Meta-Restoration Network for Blind Super-Resolution—0
Variational Deep Image RestorationCode1
Training Patch Analysis and Mining Skills for Image Restoration Deep Neural Networks—0
Mockingbird at the SIGTYP 2022 Shared Task: Two Types of Models forthe Prediction of Cognate Reflexes—0
The SIGTYP 2022 Shared Task on the Prediction of Cognate ReflexesCode0
NTIRE 2022 Challenge on Perceptual Image Quality Assessment—0
Self-supervised deep image restoration via adaptive stochastic gradient Langevin dynamicsCode1
Masked Frequency Modeling for Self-Supervised Visual Pre-TrainingCode1
Annular Computational Imaging: Capture Clear Panoramic Images through Simple LensCode1
Hypernetwork-Based Adaptive Image RestorationCode1
Toward Real-world Single Image Deraining: A New Benchmark and BeyondCode1
Robust Deep Ensemble Method for Real-world Image DenoisingCode0
Patch-based image Super Resolution using generalized Gaussian mixture model—0
Real-World Image Super-Resolution by Exclusionary Dual-LearningCode1
Priors in Deep Image Restoration and Enhancement: A SurveyCode1
Compound Multi-branch Feature Fusion for Real Image RestorationCode1
NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results—0
Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging—0
A theoretical framework for self-supervised MR image reconstruction using sub-sampling via variable density Noisier2NoiseCode1
A Survey on Hyperspectral Image Restoration: From the View of Low-Rank Tensor Approximation—0
Speckle Image Restoration without Clean Data—0
MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-ResolutionCode1
Semi-Cycled Generative Adversarial Networks for Real-World Face Super-ResolutionCode1
GenISP: Neural ISP for Low-Light Machine CognitionCode1
Physics-guided Terahertz Computational Imaging—0
PnP-ReG: Learned Regularizing Gradient for Plug-and-Play Gradient Descent—0
Deep Generalized Unfolding Networks for Image RestorationCode1
Conformer and Blind Noisy Students for Improved Image Quality AssessmentCode1
Attentive Fine-Grained Structured Sparsity for Image RestorationCode1
Show:102550
← PrevPage 17 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