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 351–375 of 1459 papers

TitleStatusHype
Multi-Expert Adaptive Selection: Task-Balancing for All-in-One Image RestorationCode1
Deformable Kernel Networks for Joint Image FilteringCode1
Accelerating Multiframe Blind Deconvolution via Deep LearningCode1
Ab-initio Contrast Estimation and Denoising of Cryo-EM ImagesCode1
Cross-Scale Internal Graph Neural Network for Image Super-ResolutionCode1
Cross Aggregation Transformer for Image RestorationCode1
Attentive Fine-Grained Structured Sparsity for Image RestorationCode1
Hierarchical Contrastive Learning for Pattern-Generalizable Image Corruption DetectionCode1
Dual Pixel Exploration: Simultaneous Depth Estimation and Image RestorationCode1
Multi-Stage Progressive Image RestorationCode1
High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented TransformerCode1
DemosaicFormer: Coarse-to-Fine Demosaicing Network for HybridEVS CameraCode1
Neural Degradation Representation Learning for All-In-One Image RestorationCode1
Diffusion State-Guided Projected Gradient for Inverse ProblemsCode1
Diffusion Priors for Variational Likelihood Estimation and Image DenoisingCode1
MOFA: A Model Simplification Roadmap for Image Restoration on Mobile DevicesCode1
Diffusion Posterior Proximal Sampling for Image RestorationCode1
Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolutionCode1
Boosting All-in-One Image Restoration via Self-Improved Privilege LearningCode1
Attention-Guided Low-Rank Tensor CompletionCode1
A Practical Contrastive Learning Framework for Single-Image Super-ResolutionCode1
Image Demoireing with Learnable Bandpass FiltersCode1
Image Generation With Neural Cellular AutomatasCode1
Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned GuidanceCode1
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasksCode1
Show:102550
← PrevPage 15 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