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 851–875 of 1459 papers

TitleStatusHype
Efficient Degradation-aware Any Image Restoration—0
Efficient Deweather Mixture-of-Experts with Uncertainty-aware Feature-wise Linear Modulation—0
Efficient Dynamic Scene Deblurring Using Spatially Variant Deconvolution Network With Optical Flow Guided Training—0
Efficient Image Restoration through Low-Rank Adaptation and Stable Diffusion XL—0
Efficient Image Restoration via Latent Consistency Flow Matching—0
Efficient Medical Image Restoration via Reliability Guided Learning in Frequency Domain—0
Efficient Progressive High Dynamic Range Image Restoration via Attention and Alignment Network—0
Elucidating and Endowing the Diffusion Training Paradigm for General Image Restoration—0
Empirical Bayesian image restoration by Langevin sampling with a denoising diffusion implicit prior—0
Empowering Image Recovery_ A Multi-Attention Approach—0
Energy-Inspired Self-Supervised Pretraining for Vision Models—0
Enhancement of Underwater Images with Statistical Model of Background Light and Optimization of Transmission Map—0
Enhance Visual Recognition under Adverse Conditions via Deep Networks—0
Enhancing Image Restoration Transformer via Adaptive Translation Equivariance—0
Enhancing Sample Generation of Diffusion Models using Noise Level Correction—0
Epigraphical Relaxation for Minimizing Layered Mixed Norms—0
EquiReg: Equivariance Regularized Diffusion for Inverse Problems—0
Equivariant Denoisers for Image Restoration—0
ERL-Net: Entangled Representation Learning for Single Image De-Raining—0
Estimating Sparse Signals with Smooth Support via Convex Programming and Block Sparsity—0
Estimation and Restoration of Compositional Degradation Using Convolutional Neural Networks—0
ESTISR: Adapting Efficient Scene Text Image Super-resolution for Real-Scenes—0
Evaluating Procedures for Establishing Generative Adversarial Network-based Stochastic Image Models in Medical Imaging—0
Evolutionary Neural Architecture Search for Image Restoration—0
Exploiting Spectral-Spatial Correlation for Coded Hyperspectral Image Restoration—0
Show:102550
← PrevPage 35 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