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 1976–2000 of 7282 papers

TitleStatusHype
Graph Adversarial Diffusion ConvolutionCode0
AMOSL: Adaptive Modality-wise Structure Learning in Multi-view Graph Neural Networks For Enhanced Unified Representation—0
M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoising—0
S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object Tracking—0
Neural Thermodynamic Integration: Free Energies from Energy-based Diffusion ModelsCode1
Generating Synthetic Net Load Data with Physics-informed Diffusion Model—0
Convergence of the denoising diffusion probabilistic models for general noise schedules—0
ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation—0
Proxy Denoising for Source-Free Domain AdaptationCode3
DEFT: Efficient Fine-Tuning of Diffusion Models by Learning the Generalised h-transformCode1
Learning-to-Cache: Accelerating Diffusion Transformer via Layer CachingCode2
Improving Pseudo Labels with Global-Local Denoising Framework for Cross-lingual Named Entity RecognitionCode1
Advancing Weakly-Supervised Audio-Visual Video Parsing via Segment-wise Pseudo Labeling—0
Diffusion Boosted Trees—0
Reservoir History Matching of the Norne field with generative exotic priors and a coupled Mixture of Experts -- Physics Informed Neural Operator Forward ModelCode3
Imitating the Functionality of Image-to-Image Models Using a Single Example—0
Diffusion Tuning: Transferring Diffusion Models via Chain of Forgetting—0
RecDiff: Diffusion Model for Social RecommendationCode2
Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data—0
Knowledge Enhanced Multi-intent Transformer Network for RecommendationCode0
Information Maximization via Variational Autoencoders for Cross-Domain Recommendation—0
Information Theoretic Text-to-Image Alignment—0
Adv-KD: Adversarial Knowledge Distillation for Faster Diffusion SamplingCode0
Mixed Diffusion for 3D Indoor Scene SynthesisCode2
Unified Directly Denoising for Both Variance Preserving and Variance Exploding Diffusion Models—0
Show:102550
← PrevPage 80 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