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 4226–4250 of 7282 papers

TitleStatusHype
Retinex Image Enhancement Based on Sequential Decomposition With a Plug-and-Play Framework—0
Denoising Masked AutoEncoders Help Robust ClassificationCode1
Masked Autoencoders for Low dose CT denoising—0
CLIP-Diffusion-LM: Apply Diffusion Model on Image CaptioningCode1
What the DAAM: Interpreting Stable Diffusion Using Cross AttentionCode2
Label-Driven Denoising Framework for Multi-Label Few-Shot Aspect Category DetectionCode1
FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck EquationCode1
LW-ISP: A Lightweight Model with ISP and Deep Learning—0
STaSy: Score-based Tabular data SynthesisCode1
Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning RulesCode1
Novel View Synthesis with Diffusion Models—0
On Distillation of Guided Diffusion ModelsCode3
Progressive Text-to-Image Generation—0
clip2latent: Text driven sampling of a pre-trained StyleGAN using denoising diffusion and CLIPCode1
Polar Encoding: A Simple Baseline Approach for Classification with Missing Values—0
Accurate Image Restoration with Attention Retractable TransformerCode1
Clean self-supervised MRI reconstruction from noisy, sub-sampled training data with Robust SSDUCode0
Diffusion Models for Graphs Benefit From Discrete State SpacesCode1
WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iteration—0
EraseNet: A Recurrent Residual Network for Supervised Document Cleaning—0
Improving Sample Quality of Diffusion Models Using Self-Attention GuidanceCode7
OCD: Learning to Overfit with Conditional Diffusion ModelsCode1
Seeing Through the Noisy Dark: Towards Real-world Low-Light Image Enhancement and Denoising—0
Deep Perceptual Enhancement for Medical Image AnalysisCode0
Automatic Summarization for Creative Writing: BART based Pipeline Method for Generating Summary of Movie Scripts—0
Show:102550
← PrevPage 170 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