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 601–625 of 1459 papers

TitleStatusHype
On the unreasonable vulnerability of transformers for image restoration -- and an easy fix—0
A Theoretically Guaranteed Quaternion Weighted Schatten p-norm Minimization Method for Color Image RestorationCode0
Physics-Driven Turbulence Image Restoration with Stochastic RefinementCode1
NTIRE 2023 Quality Assessment of Video Enhancement Challenge—0
Soft-IntroVAE for Continuous Latent space Image Super-Resolution—0
Text-guided Image Restoration and Semantic Enhancement for Text-to-Image Person RetrievalCode1
Multiscale Coarse-to-Fine Guided Screenshot DemoiréingCode0
LUCYD: A Feature-Driven Richardson-Lucy Deconvolution NetworkCode1
DRM-IR: Task-Adaptive Deep Unfolding Network for All-In-One Image Restoration—0
Latent Graph Attention for Enhanced Spatial Context—0
Dequantization and Color Transfer with Diffusion ModelsCode0
Learning Degradation-Independent Representations for Camera ISP Pipelines—0
FarSight: A Physics-Driven Whole-Body Biometric System at Large Distance and Altitude—0
Cutting-Edge Techniques for Depth Map Super-Resolution—0
ProRes: Exploring Degradation-aware Visual Prompt for Universal Image RestorationCode1
PromptIR: Prompting for All-in-One Blind Image RestorationCode2
Restoration of the JPEG Maximum Lossy Compressed Face Images with Hourglass Block based on Early Stopping Discriminator—0
Accelerating Multiframe Blind Deconvolution via Deep LearningCode1
TransRef: Multi-Scale Reference Embedding Transformer for Reference-Guided Image InpaintingCode1
Enlighten Anything: When Segment Anything Model Meets Low-Light Image EnhancementCode1
Exploring the Application of Large-scale Pre-trained Models on Adverse Weather Removal—0
Investigation of the Challenges of Underwater-Visual-Monocular-SLAM—0
Learning Image-Adaptive Codebooks for Class-Agnostic Image Restoration—0
Illumination Controllable Dehazing Network based on Unsupervised Retinex EmbeddingCode1
HQ-50K: A Large-scale, High-quality Dataset for Image RestorationCode1
Show:102550
← PrevPage 25 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