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 4876–4900 of 7282 papers

TitleStatusHype
Statistical and Computational Efficiency for Smooth Tensor Estimation with Unknown Permutations—0
Survey of Deep Learning Methods for Inverse Problems—0
Deep Noise Suppression Maximizing Non-Differentiable PESQ Mediated by a Non-Intrusive PESQNet—0
Graph Denoising with Framelet RegularizerCode0
Testing using Privileged Information by Adapting Features with Statistical Dependence—0
Deep Point Set Resampling via Gradient Fields—0
Realistic galaxy image simulation via score-based generative modelsCode1
Zero-Shot Translation using Diffusion Models—0
HW-TSC’s Participation in the WMT 2021 Triangular MT Shared Task—0
RoBLEURT Submission for WMT2021 Metrics Task—0
TSDAE: Using Transformer-based Sequential Denoising Auto-Encoderfor Unsupervised Sentence Embedding LearningCode1
Learning to Assimilate in Chaotic Dynamical SystemsCode0
Self-Verification in Image Denoising—0
Self-Supervised Speech Denoising Using Only Noisy Audio SignalsCode1
Functional Neural Networks for Parametric Image Restoration Problems—0
An Effective Image Restorer: Denoising and Luminance Adjustment for Low-photon-count Imaging—0
Unsupervised PET Reconstruction from a Bayesian Perspective—0
Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction—0
Frequency Centric Defense Mechanisms against Adversarial Examples—0
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech ProcessingCode3
Self-Denoising Neural Networks for Few Shot Learning—0
NeRV: Neural Representations for VideosCode1
Learning Continuous Face Representation with Explicit Functions—0
Generative Flows as a General Purpose Solution for Inverse ProblemsCode0
A Deep Learning Approach to Predicting Collateral Flow in Stroke Patients Using Radiomic Features from Perfusion Images—0
Show:102550
← PrevPage 196 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