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 776–800 of 1459 papers

TitleStatusHype
Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and RestorationCode2
A Validation Approach to Over-parameterized Matrix and Image Recovery—0
Near-Field SAR Image Restoration Based On Two Dimensional Spatial-Variant Deconvolution—0
Masked Face Inpainting Through Residual Attention UNetCode1
Deep Plug-and-Play Prior for Hyperspectral Image RestorationCode1
MIPI 2022 Challenge on Under-Display Camera Image Restoration: Methods and Results—0
Learning A Locally Unified 3D Point Cloud for View SynthesisCode1
Retinal Image Restoration and Vessel Segmentation using Modified Cycle-CBAM and CBAM-UNetCode1
MMV_Im2Im: An Open Source Microscopy Machine Vision Toolbox for Image-to-Image TransformationCode1
UDC-UNet: Under-Display Camera Image Restoration via U-Shape Dynamic NetworkCode1
TogetherNet: Bridging Image Restoration and Object Detection Together via Dynamic Enhancement LearningCode1
ELMformer: Efficient Raw Image Restoration with a Locally Multiplicative TransformerCode0
CAIR: Fast and Lightweight Multi-Scale Color Attention Network for Instagram Filter RemovalCode1
SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-ResolutionCode1
AT-DDPM: Restoring Faces degraded by Atmospheric Turbulence using Denoising Diffusion Probabilistic ModelsCode1
A Constrained Deformable Convolutional Network for Efficient Single Image Dynamic Scene Blind Deblurring with Spatially-Variant Motion Blur Kernels EstimationCode0
SnowFormer: Context Interaction Transformer with Scale-awareness for Single Image DesnowingCode1
Cold Diffusion: Inverting Arbitrary Image Transforms Without NoiseCode3
On a Mechanism Framework of Autoencoders—0
Learning Degradation Representations for Image DeblurringCode1
Generalizable Medical Image Segmentation via Random Amplitude Mixup and Domain-Specific Image RestorationCode1
Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object DetectionCode1
Learning Prior Feature and Attention Enhanced Image InpaintingCode1
Photon-Limited Blind Deconvolution using Unsupervised Iterative Kernel EstimationCode0
High Dynamic Range and Super-Resolution from Raw Image Bursts—0
Show:102550
← PrevPage 32 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