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 426–450 of 7282 papers

TitleStatusHype
Under-Sampled High-Dimensional Data Recovery via Symbiotic Multi-Prior Tensor Reconstruction—0
Releasing Differentially Private Event Logs Using Generative ModelsCode0
Gaussian Mixture Flow Matching ModelsCode2
DDPM Score Matching and Distribution Learning—0
REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning—0
Improved Stochastic Texture Filtering Through Sample Reuse—0
Dimension-Free Convergence of Diffusion Models for Approximate Gaussian Mixtures—0
Federated Learning for Medical Image Classification: A Comprehensive Benchmark—0
Variational Self-Supervised Learning—0
BrainMRDiff: A Diffusion Model for Anatomically Consistent Brain MRI Synthesis—0
Turbocharging Fluid Antenna Multiple Access—0
Simultaneous Motion And Noise Estimation with Event CamerasCode0
Roto-Translation Invariant Metrics on Position-Orientation Space—0
Classic Video Denoising in a Machine Learning World: Robust, Fast, and Controllable—0
On the Connection Between Diffusion Models and Molecular Dynamics—0
FaR: Enhancing Multi-Concept Text-to-Image Diffusion via Concept Fusion and Localized Refinement—0
DP-LET: An Efficient Spatio-Temporal Network Traffic Prediction Framework—0
TQD-Track: Temporal Query Denoising for 3D Multi-Object Tracking—0
Dynamic Importance in Diffusion U-Net for Enhanced Image SynthesisCode0
Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion ModelsCode1
Hide and Seek in Noise Labels: Noise-Robust Collaborative Active Learning with LLM-Powered Assistance—0
VIP: Video Inpainting Pipeline for Real World Human Removal—0
Fine-Tuning Visual Autoregressive Models for Subject-Driven GenerationCode1
Analytical Discovery of Manifold with Machine Learning—0
Enhancing LLM Robustness to Perturbed Instructions: An Empirical StudyCode0
Show:102550
← PrevPage 18 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