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 401–450 of 1459 papers

TitleStatusHype
Burst Image Restoration and EnhancementCode1
Restormer: Efficient Transformer for High-Resolution Image RestorationCode1
Burstormer: Burst Image Restoration and Enhancement TransformerCode1
Are Deep Neural Architectures Losing Information? Invertibility Is IndispensableCode1
CAIR: Fast and Lightweight Multi-Scale Color Attention Network for Instagram Filter RemovalCode1
Half Wavelet Attention on M-Net+ for Low-Light Image EnhancementCode1
Image Restoration via Frequency SelectionCode1
Revisiting Implicit Neural Representations in Low-Level VisionCode1
GenISP: Neural ISP for Low-Light Machine CognitionCode1
Graph Image Prior for Unsupervised Dynamic Cardiac Cine MRI ReconstructionCode1
A Regularization-Guided Equivariant Approach for Image RestorationCode1
Robust Unsupervised StyleGAN Image RestorationCode1
RPBG: Towards Robust Neural Point-based Graphics in the WildCode1
Divide-and-Conquer Posterior Sampling for Denoising Diffusion PriorsCode1
Generating Aligned Pseudo-Supervision from Non-Aligned Data for Image Restoration in Under-Display CameraCode1
Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-ExpertsCode1
DnSwin: Toward Real-World Denoising via Continuous Wavelet Sliding-TransformerCode1
EDPN: Enhanced Deep Pyramid Network for Blurry Image RestorationCode1
Generative Modeling with Optimal Transport MapsCode1
Selective Residual M-Net for Real Image DenoisingCode1
GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather ConditionsCode1
Attention-Guided Low-Rank Tensor CompletionCode1
DREB-Net: Dual-stream Restoration Embedding Blur-feature Fusion Network for High-mobility UAV Object DetectionCode1
Chain-of-Restoration: Multi-Task Image Restoration Models are Zero-Shot Step-by-Step Universal Image RestorersCode1
Self-Supervised Image Restoration with Blurry and Noisy PairsCode1
Self-supervised Monocular Underwater Depth Recovery, Image Restoration, and a Real-sea Video DatasetCode1
Spatio-Temporal SAR-Optical Data Fusion for Cloud Removal via a Deep Hierarchical ModelCode1
DRT: A Lightweight Single Image Deraining Recursive TransformerCode1
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasksCode1
Generalizable Medical Image Segmentation via Random Amplitude Mixup and Domain-Specific Image RestorationCode1
Attention Cube Network for Image RestorationCode1
All-in-One Image Compression and RestorationCode1
Single Underwater Image Restoration by Contrastive LearningCode1
Dual Pixel Exploration: Simultaneous Depth Estimation and Image RestorationCode1
A Mountain-Shaped Single-Stage Network for Accurate Image RestorationCode1
SS-BSN: Attentive Blind-Spot Network for Self-Supervised Denoising with Nonlocal Self-SimilarityCode1
Adaptive Blind All-in-One Image RestorationCode1
Stochastic Frequency Masking to Improve Super-Resolution and Denoising NetworksCode1
GroupCDL: Interpretable Denoising and Compressed Sensing MRI via Learned Group-Sparsity and Circulant AttentionCode1
FriendNet: Detection-Friendly Dehazing NetworkCode1
Style-Guided Shadow RemovalCode1
Freqformer: Image-Demoiréing Transformer via Efficient Frequency DecompositionCode1
From Rank Estimation to Rank Approximation: Rank Residual Constraint for Image RestorationCode1
Forward-only Diffusion Probabilistic ModelsCode1
A Comparative Study of Image Restoration Networks for General Backbone Network DesignCode1
From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral PerspectiveCode1
FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly DetectionCode1
A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image RestorationCode1
The 2018 PIRM Challenge on Perceptual Image Super-resolutionCode1
Flare-Free Vision: Empowering Uformer with Depth InsightsCode1
Show:102550
← PrevPage 9 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