mlsanityData to 14 Oct 2026

D4PM: A Dual-branch Driven Denoising Diffusion Probabilistic Model with Joint Posterior Diffusion Sampling for EEG Artifacts Removal

arXiv 2509.14302 ↗First posted 17 Sep 2025eess.IVcited by 0

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Artifact removal is critical for accurate analysis and interpretation of Electroencephalogram (EEG) signals. Traditional methods perform poorly with strong artifact-EEG correlations or single-channel data. Recent advances in diffusion-based generative models have demonstrated strong potential for EEG denoising, notably improving fine-grained noise suppression and reducing over-smoothing. However, existing methods face two main limitations: lack of temporal modeling limits interpretability and the use of single-artifact training paradigms ignore inter-artifact differences. To address these issues, we propose D4PM, a dual-branch driven denoising diffusion probabilistic model that unifies multi-type artifact removal. We introduce a dual-branch conditional diffusion architecture to implicitly model the data distribution of clean EEG and artifacts. A joint posterior sampling strategy is further designed to collaboratively integrate complementary priors for high-fidelity EEG reconstruction. Extensive experiments on two public datasets show that D4PM delivers superior denoising. It achieves new state-of-the-art performance in EOG artifact removal, outperforming all publicly available baselines. The code is available at https://github.com/flysnow1024/D4PM.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 4 of its 23 references that are in the map. First posted on arXiv 17 Sep 2025.

Builds on

4 of 23 references.

References · 4

  1. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
  2. 2020A novel convolutional neural network model to remove muscle artifacts from EEGcited by 12
  3. 2021EEGDnet: Fusing Non-Local and Local Self-Similarity for 1-D EEG Signal Denoising with 2-D Transformercited by 11
  4. 2021Toward Open-World Electroencephalogram Decoding Via Deep Learning: A Comprehensive Surveycited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025ArtifactGen: Benchmarking WGAN-GP vs Diffusion for Label-Aware EEG Artifact Synthesis
  2. 2025EEGDM: EEG Representation Learning via Generative Diffusion Model
  3. 2024Improving EEG Classification Through Randomly Reassembling Original and Generated Data with Transformer-based Diffusion Models
  4. 2023Brain-Driven Representation Learning Based on Diffusion Model
  5. 2025EEGDM: Learning EEG Representation with Latent Diffusion Model
  6. 2024Synthesizing EEG Signals from Event-Related Potential Paradigms with Conditional Diffusion Models
  7. 2025A Statistical Mixture-of-Experts Framework for EMG Artifact Removal in EEG: Empirical Insights and a Proof-of-Concept Application
  8. 2025Step-Aware Residual-Guided Diffusion for EEG Spatial Super-Resolution