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 1126–1150 of 1459 papers

TitleStatusHype
The Power of Triply Complementary Priors for Image Compressive Sensing—0
PMHLD: Patch Map Based Hybrid Learning DehazeNet for Single Image Haze RemovalCode1
HiFaceGAN: Face Renovation via Collaborative Suppression and ReplenishmentCode1
Hyperspectral Image Restoration via Global Total Variation Regularized Local nonconvex Low-Rank matrix Approximation—0
NTIRE 2020 Challenge on Image Demoireing: Methods and Results—0
Enhancing Intrinsic Adversarial Robustness via Feature Pyramid DecoderCode1
Neural Differential Equations for Single Image Super-resolution—0
Unsupervised Lesion Detection via Image Restoration with a Normative Prior—0
Pyramid Attention Networks for Image RestorationCode1
Attention Based Real Image RestorationCode0
Virtual SAR: A Synthetic Dataset for Deep Learning based Speckle Noise Reduction Algorithms—0
Microscopy Image Restoration using Deep Learning on W2SCode1
Distributed Learning and Inference with Compressed Images—0
Bringing Old Photos Back to LifeCode3
Moire Image Restoration using Multi Level Hyper Vision NetCode0
KD-MRI: A knowledge distillation framework for image reconstruction and image restoration in MRI workflowCode1
Real-world Person Re-Identification via Degradation Invariance Learning—0
Deblurring using Analysis-Synthesis Networks Pair—0
Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New StrategyCode1
Image Demoireing with Learnable Bandpass FiltersCode1
Exploiting Deep Generative Prior for Versatile Image Restoration and ManipulationCode1
A Set-Theoretic Study of the Relationships of Image Models and Priors for Restoration Problems—0
Learning Invariant Representation for Unsupervised Image RestorationCode1
Blur, Noise, and Compression Robust Generative Adversarial Networks—0
CycleISP: Real Image Restoration via Improved Data SynthesisCode1
Show:102550
← PrevPage 46 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