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 4426–4450 of 7282 papers

TitleStatusHype
Theoretical Perspectives on Deep Learning Methods in Inverse Problems—0
SPI-GAN: Denoising Diffusion GANs with Straight-Path Interpolations—0
Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance MatchingCode1
Extended U-Net for Speaker Verification in Noisy EnvironmentsCode1
DeStripe: A Self2Self Spatio-Spectral Graph Neural Network with Unfolded Hessian for Stripe Artifact Removal in Light-sheet Microscopy—0
Diffusion Deformable Model for 4D Temporal Medical Image GenerationCode1
Noise-aware Physics-informed Machine Learning for Robust PDE DiscoveryCode0
Defense against adversarial attacks on deep convolutional neural networks through nonlocal denoising—0
Using Autoencoders on Differentially Private Federated Learning GANsCode0
Megapixel Image Generation with Step-Unrolled Denoising AutoencodersCode0
Self-Supervised Training with Autoencoders for Visual Anomaly Detection—0
DDPM-CD: Denoising Diffusion Probabilistic Models as Feature Extractors for Change DetectionCode2
Entropy-driven Sampling and Training Scheme for Conditional Diffusion GenerationCode1
Speaker-Independent Microphone Identification in Noisy Conditions—0
A Simple Baseline for Video Restoration with Grouped Spatial-temporal ShiftCode1
On Grid Compressive Sampling for Spherical Field Measurements in Acoustics—0
Questions Are All You Need to Train a Dense Passage RetrieverCode1
KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP—0
(Certified!!) Adversarial Robustness for Free!Code1
Efficient and Flexible Sublabel-Accurate Energy MinimizationCode0
SJ-HD^2R: Selective Joint High Dynamic Range and Denoising Imaging for Dynamic Scenes—0
0/1 Deep Neural Networks via Block Coordinate Descent—0
Diffusion models as plug-and-play priorsCode2
VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix—0
To Dereverb Or Not to Dereverb? Perceptual Studies On Real-Time Dereverberation Targets—0
Show:102550
← PrevPage 178 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