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 5901–5950 of 7282 papers

TitleStatusHype
Utilizing the Wavelet Transform's Structure in Compressed Sensing—0
Reconstructing the Noise Manifold for Image Denoising—0
Free-breathing Cardiovascular MRI Using a Plug-and-Play Method with Learned Denoiser—0
GPU acceleration of NL-means, BM3D and VBM3D—0
Translating Diffusion, Wavelets, and Regularisation into Residual Networks—0
Differentiable Forward and Backward Fixed-Point Iteration Layers—0
SPN-CNN: Boosting Sensor-Based Source Camera Attribution With Deep Learning—0
Iterative Data Programming for Expanding Text Classification Corpora—0
Generative Modeling with Denoising Auto-Encoders and Langevin Sampling—0
Noise2Inverse: Self-supervised deep convolutional denoising for tomographyCode1
Point Spread Function Modelling for Wide Field Small Aperture Telescopes with a Denoising Autoencoder—0
Spatial-Adaptive Network for Single Image DenoisingCode1
An optimized pipeline for functional connectivity analysis in the rat brainCode0
Proximal Gradient Algorithms: Applications in Signal Processing—0
Handling noise in image deblurring via joint learning—0
Ensemble Noise Simulation to Handle Uncertainty about Gradient-based Adversarial Attacks—0
Detecting Changes in Asset Co-Movement Using the Autoencoder Reconstruction Ratio—0
Segmentation of Retinal Low-Cost Optical Coherence Tomography Images using Deep Learning—0
Model-Based Deep Learning for Reconstruction of Joint k-q Under-sampled High Resolution Diffusion MRI—0
Multilingual Denoising Pre-training for Neural Machine TranslationCode1
Depth Completion Using a View-constrained Deep Prior—0
HRFA: High-Resolution Feature-based Attack—0
CNN-Based Real-Time Parameter Tuning for Optimizing Denoising Filter PerformanceCode0
A deep network for sinogram and CT image reconstructionCode1
CNN-based InSAR Denoising and Coherence MetricCode1
Image denoising via K-SVD with primal-dual active set algorithm—0
Sinogram super-resolution and denoising convolutional neural network (SRCN) for limited data photoacoustic tomography—0
Code-Bridged Classifier (CBC): A Low or Negative Overhead Defense for Making a CNN Classifier Robust Against Adversarial Attacks—0
Masking schemes for universal marginalisers—0
Adaptive Direction-Guided Structure Tensor Total Variation—0
Autoencoders as Weight Initialization of Deep Classification Networks for Cancer versus Cancer Studies—0
Towards Deep Unsupervised SAR Despeckling with Blind-Spot Convolutional Neural Networks—0
A Differentiable Perceptual Audio Metric Learned from Just Noticeable DifferencesCode1
Self-Supervised Fast Adaptation for Denoising via Meta-Learning—0
Learning Generative Models using Denoising Density EstimatorsCode0
Limited Angle Tomography for Transmission X-Ray Microscopy Using Deep Learning—0
Hypergraph Spectral Analysis and Processing in 3D Point Cloud—0
Speech Enhancement based on Denoising Autoencoder with Multi-branched EncodersCode0
Implementation of the VBM3D Video Denoising Method and Some VariantsCode1
Image Speckle Noise Denoising by a Multi-Layer Fusion Enhancement Method based on Block Matching and 3D Filtering—0
InSAR Phase Denoising: A Review of Current Technologies and Future Directions—0
TED: A Pretrained Unsupervised Summarization Model with Theme Modeling and Denoising—0
A Machine Learning Imaging Core using Separable FIR-IIR Filters—0
First image then video: A two-stage network for spatiotemporal video denoisingCode0
ATHENA: A Framework based on Diverse Weak Defenses for Building Adversarial DefenseCode1
Compressive sensing with un-trained neural networks: Gradient descent finds a smooth approximationCode1
VideoOneNet: Bidirectional Convolutional Recurrent OneNet with Trainable Data Steps for Video ProcessingCode0
Label-Noise Robust Domain Adaptation—0
A Total Variation Denoising Method Based on Median Filter and Phase Consistency—0
Stacked DeBERT: All Attention in Incomplete Data for Text ClassificationCode1
Show:102550
← PrevPage 119 of 146Next →
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