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 426–450 of 1459 papers

TitleStatusHype
MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image RecoveryCode1
MOFA: A Model Simplification Roadmap for Image Restoration on Mobile DevicesCode1
DRT: A Lightweight Single Image Deraining Recursive TransformerCode1
Attention-Guided Low-Rank Tensor CompletionCode1
Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolutionCode1
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasksCode1
Principal Uncertainty Quantification with Spatial Correlation for Image Restoration ProblemsCode1
Multi-dimensional Visual Prompt Enhanced Image Restoration via Mamba-Transformer AggregationCode1
Dual Pixel Exploration: Simultaneous Depth Estimation and Image RestorationCode1
CLEARER: Multi-Scale Neural Architecture Search for Image RestorationCode1
Multi-Expert Adaptive Selection: Task-Balancing for All-in-One Image RestorationCode1
Attention Cube Network for Image RestorationCode1
A Mountain-Shaped Single-Stage Network for Accurate Image RestorationCode1
Prompt-based Ingredient-Oriented All-in-One Image RestorationCode1
Dynamic Contrastive Knowledge Distillation for Efficient Image RestorationCode1
ProRes: Exploring Degradation-aware Visual Prompt for Universal Image RestorationCode1
Learning Distortion Invariant Representation for Image Restoration from A Causality PerspectiveCode1
PMHLD: Patch Map Based Hybrid Learning DehazeNet for Single Image Haze RemovalCode1
A Comparative Study of Image Restoration Networks for General Backbone Network DesignCode1
Enlighten Anything: When Segment Anything Model Meets Low-Light Image EnhancementCode1
Navigating the GAN Parameter Space for Semantic Image EditingCode1
Early Exit or Not: Resource-Efficient Blind Quality Enhancement for Compressed ImagesCode1
(ASNA) An Attention-based Siamese-Difference Neural Network with Surrogate Ranking Loss function for Perceptual Image Quality AssessmentCode1
A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image RestorationCode1
Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models trained on Corrupted DataCode1
Show:102550
← PrevPage 18 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