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 876–900 of 1459 papers

TitleStatusHype
Enriched CNN-Transformer Feature Aggregation Networks for Super-ResolutionCode1
Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning—0
MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image InpaintingCode1
TAPE: Task-Agnostic Prior Embedding for Image Restoration—0
Self-Supervised Face Image Restoration with a One-Shot ReferenceCode1
Adaptive Cross-Layer Attention for Image RestorationCode1
HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging—0
Selective Residual M-Net for Real Image DenoisingCode1
Half Wavelet Attention on M-Net+ for Low-Light Image EnhancementCode1
SUNet: Swin Transformer UNet for Image DenoisingCode2
Alternative design of DeepPDNet in the context of image restoration—0
Task Adaptive Network for Image Restoration With Combined Degradation FactorsCode1
Ab-initio Contrast Estimation and Denoising of Cryo-EM ImagesCode1
Deep Constrained Least Squares for Blind Image Super-ResolutionCode2
Zero-Reference Image Restoration for Under-Display Camera of UAVCode1
Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex RegularizationCode1
VRT: A Video Restoration TransformerCode3
Unsupervised Denoising of Retinal OCT with Diffusion Probabilistic ModelCode1
Denoising Diffusion Restoration ModelsCode2
Revisiting L1 Loss in Super-Resolution: A Probabilistic View and Beyond—0
MAXIM: Multi-Axis MLP for Image ProcessingCode3
Tensor Wiener Filter—0
RestoreDet: Degradation Equivariant Representation for Object Detection in Low Resolution Images—0
RFormer: Transformer-based Generative Adversarial Network for Real Fundus Image Restoration on A New Clinical BenchmarkCode1
FaceQgen: Semi-Supervised Deep Learning for Face Image Quality AssessmentCode0
Show:102550
← PrevPage 36 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