VAMP-Diff: VampPrior Latent Diffusion for Photoplethysmography Modeling
For researchers in physiological signal processing, this work addresses the lack of both high-fidelity generation and inference in PPG modeling, though improvements are incremental over existing diffusion and VAE methods.
VAMP-Diff introduces a variational diffusion model for PPG signals that combines a temporal encoder, conditional diffusion decoder, and VampPrior regularization, achieving sharper waveform reconstruction and better preservation of heart rate and respiratory rate information compared to Gaussian-prior baselines on the CapnoBase dataset.
Photoplethysmography (PPG) has become a ubiquitous physiological signal; however, current generative models still struggle to preserve realistic waveform morphology and learn a latent structure that captures cardiac and respiratory physiology. PPG generators trained with adversarial losses can produce plausible waveforms, but provide no inference path from a real signal to a latent representation. Variational autoencoders, on the other hand, map the PPG data to latent codes, although their decoders often blur systolic upstrokes and dampen amplitude and spectral details. Diffusion models improve waveform fidelity, but typically lack an inference path for reconstruction and physiological analysis. We propose VampPrior Latent Diffusion (VAMP-Diff), a jointly trained variational diffusion model that combines a temporal PPG encoder, a conditional one-dimensional diffusion decoder, and VampPrior regularization on a compact pooled latent. The model uses full temporal latent during diffusion reconstruction, giving the decoder access to beat timing and morphology while generating samples from learned VampPrior components instead of a fixed Gaussian prior. We demonstrate on the CapnoBase dataset that VAMP-Diff produces realistic PPG signals, reconstructs sharper physiological waveforms than Gaussian-prior baselines, preserves heart-rate information, maintains respiratory-rate consistency, and is sensitive to waveform corruptions through reconstruction error.