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

Showing 201225 of 1459 papers

TitleStatusHype
Burstormer: Burst Image Restoration and Enhancement TransformerCode1
CAIR: Fast and Lightweight Multi-Scale Color Attention Network for Instagram Filter RemovalCode1
Diffusion Posterior Proximal Sampling for Image RestorationCode1
Diffusion Priors for Variational Likelihood Estimation and Image DenoisingCode1
A Regularization-Guided Equivariant Approach for Image RestorationCode1
Generating Aligned Pseudo-Supervision from Non-Aligned Data for Image Restoration in Under-Display CameraCode1
Fully Unsupervised Diversity Denoising with Convolutional Variational AutoencodersCode1
BlindDiff: Empowering Degradation Modelling in Diffusion Models for Blind Image Super-ResolutionCode1
GroupCDL: Interpretable Denoising and Compressed Sensing MRI via Learned Group-Sparsity and Circulant AttentionCode1
Devil is in the Uniformity: Exploring Diverse Learners within Transformer for Image RestorationCode1
DnSwin: Toward Real-World Denoising via Continuous Wavelet Sliding-TransformerCode1
Hierarchical Contrastive Learning for Pattern-Generalizable Image Corruption DetectionCode1
High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented TransformerCode1
Bitstream-Corrupted JPEG Images are Restorable: Two-stage Compensation and Alignment Framework for Image RestorationCode1
Annular Computational Imaging: Capture Clear Panoramic Images through Simple LensCode1
Real-time 6K Image Rescaling with Rate-distortion OptimizationCode1
CLEARER: Multi-Scale Neural Architecture Search for Image RestorationCode1
Adaptive Blind All-in-One Image RestorationCode1
BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image RestorationCode1
Image Generation With Neural Cellular AutomatasCode1
As if by magic: self-supervised training of deep despeckling networks with MERLINCode1
Image Restoration by Iterative Denoising and Backward ProjectionsCode1
(ASNA) An Attention-based Siamese-Difference Neural Network with Surrogate Ranking Loss function for Perceptual Image Quality AssessmentCode1
ConStyle v2: A Strong Prompter for All-in-One Image RestorationCode1
DemosaicFormer: Coarse-to-Fine Demosaicing Network for HybridEVS CameraCode1
Show:102550
← PrevPage 9 of 59Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1OneRestoreAverage PSNR (dB)28.72Unverified
2SRUDCAverage PSNR (dB)27.64Unverified
3RestormerAverage PSNR (dB)26.99Unverified
4WGWSNetAverage PSNR (dB)26.96Unverified
5DGUNetAverage PSNR (dB)26.92Unverified
6OKNetAverage PSNR (dB)26.33Unverified
7MIRNetAverage PSNR (dB)25.97Unverified
8PromptIRAverage PSNR (dB)25.9Unverified
9MPRNetAverage PSNR (dB)25.47Unverified
10MIRNetv2Average PSNR (dB)25.37Unverified
#ModelMetricClaimedVerifiedStatus
1ESDNet-LPSNR22.42Unverified
2ESDNetPSNR22.12Unverified
#ModelMetricClaimedVerifiedStatus
1730L37Unverified