SOTAVerified

Denoising

Denoising is a task in image processing and computer vision that aims to remove or reduce noise from an image. Noise can be introduced into an image due to various reasons, such as camera sensor limitations, lighting conditions, and compression artifacts. The goal of denoising is to recover the original image, which is considered to be noise-free, from a noisy observation.

( Image credit: Beyond a Gaussian Denoiser )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2926–2950 of 7282 papers

TitleStatusHype
A Chebyshev Confidence Guided Source-Free Domain Adaptation Framework for Medical Image Segmentation—0
Style Description based Text-to-Speech with Conditional Prosodic Layer Normalization based Diffusion GAN—0
Interacting Diffusion Processes for Event Sequence ForecastingCode0
CodeFusion: A Pre-trained Diffusion Model for Code Generation—0
A multi-artifact EEG denoising by frequency-based deep learning—0
Single channel speech enhancement by colored spectrograms—0
Likelihood-based Out-of-Distribution Detection with Denoising Diffusion Probabilistic Models—0
Improving Denoising Diffusion Models via Simultaneous Estimation of Image and Noise—0
Towards Unifying Diffusion Models for Probabilistic Spatio-Temporal Graph Learning—0
SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose EstimationCode1
Multi-scale Diffusion Denoised SmoothingCode1
RAEDiff: Denoising Diffusion Probabilistic Models Based Reversible Adversarial Examples Self-Generation and Self-Recovery—0
FuXi-Extreme: Improving extreme rainfall and wind forecasts with diffusion model—0
Resurrecting Label Propagation for Graphs with Heterophily and Label NoiseCode0
Fuse Your Latents: Video Editing with Multi-source Latent Diffusion ModelsCode0
Discrete Diffusion Modeling by Estimating the Ratios of the Data DistributionCode2
DiffRef3D: A Diffusion-based Proposal Refinement Framework for 3D Object Detection—0
Fine tuning Pre trained Models for Robustness Under Noisy Labels—0
On the Inherent Privacy Properties of Discrete Denoising Diffusion Models—0
DALE: Generative Data Augmentation for Low-Resource Legal NLPCode1
Learned, uncertainty-driven adaptive acquisition for photon-efficient scanning microscopy—0
Complex Image Generation SwinTransformer Network for Audio DenoisingCode0
Improving Diffusion Models for ECG Imputation with an Augmented Template Prior—0
DeepOrientation: convolutional neural network for fringe pattern orientation map estimationCode0
Reliable Generation of Privacy-preserving Synthetic Electronic Health Record Time Series via Diffusion ModelsCode1
Show:102550
← PrevPage 118 of 292Next →
All datasetsDarmstadt Noise DatasetDIV2KDNDiris

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SINDyPSNR81—Unverified
2Pixel-shuffling DownsamplingPSNR38.4—Unverified
3TWSCPSNR37.93—Unverified
4CBDNet(Syn)PSNR37.57—Unverified
5MCWNNMPSNR37.38—Unverified
6Han et alPSNR35.95—Unverified
7FFDNetPSNR34.4—Unverified
8TNRDPSNR33.65—Unverified
9CDnCNN-BPSNR32.43—Unverified
10NLRNPSNR30.8—Unverified
#ModelMetricClaimedVerifiedStatus
1DRUnet_Poisson_0.01Average PSNR (dB)33.92—Unverified
#ModelMetricClaimedVerifiedStatus
1DRANetAverage PSNR39.64—Unverified
#ModelMetricClaimedVerifiedStatus
1PCNN+RL+HMEAverage84.61—Unverified