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 2676–2700 of 7282 papers

TitleStatusHype
On Inference Stability for Diffusion ModelsCode0
Active contours driven by local and global intensity fitting energy with application to SAR image segmentation and its fast solvers—0
SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion ProcessCode2
GazeMoDiff: Gaze-guided Diffusion Model for Stochastic Human Motion Prediction—0
Diffusing More Objects for Semi-Supervised Domain Adaptation with Less Labeling—0
Optimizing Diffusion Noise Can Serve As Universal Motion Priors—0
Bayesian ECG reconstruction using denoising diffusion generative models—0
SPIRE: Semantic Prompt-Driven Image Restoration—0
Learning a Diffusion Model Policy from Rewards via Q-Score MatchingCode1
Towards Detailed Text-to-Motion Synthesis via Basic-to-Advanced Hierarchical Diffusion Model—0
PolyDiff: Generating 3D Polygonal Meshes with Diffusion Models—0
Unified framework for diffusion generative models in SO(3): applications in computer vision and astrophysics—0
MagicScroll: Nontypical Aspect-Ratio Image Generation for Visual Storytelling via Multi-Layered Semantic-Aware Denoising—0
A novel diffusion recommendation algorithm based on multi-scale cnn and residual lstm—0
Unraveling the Temporal Dynamics of the Unet in Diffusion Models—0
Bayes-Optimal Unsupervised Learning for Channel Estimation in Near-Field Holographic MIMO—0
Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention ModulationCode1
NM-FlowGAN: Modeling sRGB Noise without Paired Images using a Hybrid Approach of Normalizing Flows and GANCode1
MVHuman: Tailoring 2D Diffusion with Multi-view Sampling For Realistic 3D Human Generation—0
Tell Me What You See: Text-Guided Real-World Image Denoising—0
CAGE: Controllable Articulation GEneration—0
Fast Sampling generative model for Ultrasound image reconstruction—0
Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model InferenceCode2
DreamTalk: When Emotional Talking Head Generation Meets Diffusion Probabilistic ModelsCode3
PPFM: Image denoising in photon-counting CT using single-step posterior sampling Poisson flow generative modelsCode1
Show:102550
← PrevPage 108 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