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 51–75 of 1459 papers

TitleStatusHype
Compressed Image Generation with Denoising Diffusion Codebook ModelsCode2
Universal Image Restoration Pre-training via Degradation ClassificationCode2
MB-TaylorFormer V2: Improved Multi-branch Linear Transformer Expanded by Taylor Formula for Image RestorationCode2
Navigating Image Restoration with VAR's Distribution Alignment PriorCode2
Varformer: Adapting VAR's Generative Prior for Image RestorationCode2
MaIR: A Locality- and Continuity-Preserving Mamba for Image RestorationCode2
MWFormer: Multi-Weather Image Restoration Using Degradation-Aware TransformersCode2
EnsIR: An Ensemble Algorithm for Image Restoration via Gaussian Mixture ModelsCode2
An Intelligent Agentic System for Complex Image Restoration ProblemsCode2
LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image RestorationCode2
ReFIR: Grounding Large Restoration Models with Retrieval AugmentationCode2
Learning Efficient and Effective Trajectories for Differential Equation-based Image RestorationCode2
PnP-Flow: Plug-and-Play Image Restoration with Flow MatchingCode2
Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image RestorationCode2
Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image RestorationCode2
HAIR: Hypernetworks-based All-in-One Image RestorationCode2
Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse ProblemsCode2
Restore-RWKV: Efficient and Effective Medical Image Restoration with RWKVCode2
Improving Diffusion Inverse Problem Solving with Decoupled Noise AnnealingCode2
DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration ModelsCode2
Denoising as Adaptation: Noise-Space Domain Adaptation for Image RestorationCode2
Revitalizing Convolutional Network for Image RestorationCode2
DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and Landmark-Guided TransformerCode2
Correlation Matching Transformation Transformers for UHD Image RestorationCode2
All-In-One Medical Image Restoration via Task-Adaptive RoutingCode2
Show:102550
← PrevPage 3 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