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 1276–1300 of 1459 papers

TitleStatusHype
Deep Learning-Based Channel EstimationCode0
Cryo-CARE: Content-Aware Image Restoration for Cryo-Transmission Electron Microscopy DataCode0
Weighted Sigmoid Gate Unit for an Activation Function of Deep Neural Network—0
Active image restoration—0
The 2018 PIRM Challenge on Perceptual Image Super-resolutionCode1
Non-blind Image Restoration Based on Convolutional Neural Network—0
Reconstruction-based Pairwise Depth Dataset for Depth Image Enhancement Using CNN—0
Burst Image Deblurring Using Permutation Invariant Convolutional Neural Networks—0
Performance Analysis of Plug-and-Play ADMM: A Graph Signal Processing Perspective—0
CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE)—0
X-GANs: Image Reconstruction Made Easy for Extreme Cases—0
The Power of Complementary Regularizers: Image Recovery via Transform Learning and Low-Rank Modeling—0
Physics-Based Generative Adversarial Models for Image Restoration and Beyond—0
Deep Graph Laplacian Regularization for Robust Denoising of Real ImagesCode0
Multi-bin Trainable Linear Unit for Fast Image Restoration Networks—0
Linkage between piecewise constant Mumford-Shah model and ROF model and its virtue in image segmentation—0
Learning Hybrid Sparsity Prior for Image Restoration: Where Deep Learning Meets Sparse Coding—0
Learning Generic Diffusion Processes for Image Restoration—0
Vehicle Image Generation Going Well with The Surroundings—0
External Patch-Based Image Restoration Using Importance Sampling—0
Image Restoration Using Conditional Random Fields and Scale Mixtures of Gaussians—0
From Rank Estimation to Rank Approximation: Rank Residual Constraint for Image RestorationCode1
Improved Techniques for Learning to Dehaze and Beyond: A Collective StudyCode0
Latent Convolutional ModelsCode0
Generative Adversarial Networks and Perceptual Losses for Video Super-Resolution—0
Show:102550
← PrevPage 52 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