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 151–175 of 1459 papers

TitleStatusHype
A Universal Scale-Adaptive Deformable Transformer for Image Restoration across Diverse ArtifactsCode1
Zero-Shot Image Restoration Using Few-Step Guidance of Consistency Models (and Beyond)Code1
Underwater Image Restoration via Polymorphic Large Kernel CNNsCode1
Multi-dimensional Visual Prompt Enhanced Image Restoration via Mamba-Transformer AggregationCode1
Unified Image Restoration and Enhancement: Degradation Calibrated Cycle Reconstruction Diffusion ModelCode1
Dynamic Contrastive Knowledge Distillation for Efficient Image RestorationCode1
OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offsCode1
Modeling Dual-Exposure Quad-Bayer Patterns for Joint Denoising and DeblurringCode1
Phaseformer: Phase-based Attention Mechanism for Underwater Image Restoration and BeyondCode1
Adaptive Blind All-in-One Image RestorationCode1
PromptHSI: Universal Hyperspectral Image Restoration with Vision-Language Modulated Frequency AdaptationCode1
Joint multi-dimensional dynamic attention and transformer for general image restorationCode1
High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented TransformerCode1
Diffusion Priors for Variational Likelihood Estimation and Image DenoisingCode1
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
TANet: Triplet Attention Network for All-In-One Adverse Weather Image RestorationCode1
Diffusion State-Guided Projected Gradient for Inverse ProblemsCode1
Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEsCode1
Towards Real-World Adverse Weather Image Restoration: Enhancing Clearness and Semantics with Vision-Language ModelsCode1
OAPT: Offset-Aware Partition Transformer for Double JPEG Artifacts RemovalCode1
Re-boosting Self-Collaboration Parallel Prompt GAN for Unsupervised Image RestorationCode1
Unsupervised Variational Translator for Bridging Image Restoration and High-Level Vision TasksCode1
UniProcessor: A Text-induced Unified Low-level Image ProcessorCode1
Multi-Expert Adaptive Selection: Task-Balancing for All-in-One Image RestorationCode1
Show:102550
← PrevPage 7 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