EUVIMEDEUVIMED entdecken
Crossref

PhysDiff: Physiology-based Dynamicity Disentangled Diffusion Model for Remote Physiological Measurement

Wei Qian, Gaoji Su, Dan Guo, Jinxing Zhou, Xiaobai Li, Bin Hu, Shengeng Tang, Meng Wang

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (6) · 6568-6576

DOI: 10.1609/aaai.v39i6.32704 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Wei Qian und 7 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent works on remote PhotoPlethysmoGraphy (rPPG) estimation typically use techniques like CNNs and Transformers to encode implicit features from facial videos for prediction. These methods learn to directly map facial videos to the static values of rPPG signals, overlooking the inherent dynamic characteristics of rPPG sequence. Moreover, the rPPG signal is extremely weak and highly susceptible to interference from various sources of noise, including illumination conditions, head movements, and variations in skin tone. To address these limitations, we propose a Physiology-based dynamicity disentangled diffusion (PhysDiff) model particularly designed for robust rPPG estimation. PhysDiff leverages the diffusion model to learn the distribution of quasi-periodic rPPG signal and uses a dynamicity disentanglement strategy to capture two dynamic characteristics in temporal rPPG signal, i.e., trend and amplitude. This disentanglement is motivated by the underlying dynamic physiological processes of vasodilation and vasoconstriction, ensuring a more precise representation of the rPPG signal. The disentangled components are then used as pivotal conditions in the proposed spatial-temporal hybrid denoiser for rPPG reconstruction. Besides, we introduce a periodicity-based multi-hypothesis selection strategy in model inference, which compares the natural periodicity of multiple generated rPPG hypotheses and selects the most favorable one as the final prediction. Extensive experiments on four datasets demonstrate that our PhysDiff significantly outperforms prior methods on both intra-dataset and cross-dataset testing.

Zitieren

APA

Qian, W., Su, G., Guo, D., Zhou, J., Li, X., Hu, B., Tang, S., & Wang, M. (2025). PhysDiff: Physiology-based Dynamicity Disentangled Diffusion Model for Remote Physiological Measurement. Proceedings of the AAAI Conference on Artificial Intelligence, 39(6), 6568-6576. https://doi.org/10.1609/aaai.v39i6.32704

Vancouver

Qian W, Su G, Guo D, Zhou J, Li X, Hu B, et al. PhysDiff: Physiology-based Dynamicity Disentangled Diffusion Model for Remote Physiological Measurement. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(6):6568-6576. doi:10.1609/aaai.v39i6.32704

BibTeX
@article{Qian2025,
  author = {Qian, Wei and Su, Gaoji and Guo, Dan and Zhou, Jinxing and Li, Xiaobai and Hu, Bin and Tang, Shengeng and Wang, Meng},
  title = {PhysDiff: Physiology-based Dynamicity Disentangled Diffusion Model for Remote Physiological Measurement},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {6},
  pages = {6568--6576},
  doi = {10.1609/aaai.v39i6.32704}
}
Kostenlos starten →