Cylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal Transformation

Key points

• Paired translation between quasiperiodic physiological waveforms (i.e., recovering a target oscillatory signal from the source) is central to the interpretation of cardiovascular signals derived from wearables placed at different body locations.1
• We show that the standard affine path used in flow matching distorts intermediate amplitude and instantaneous frequency when interpolating between quasiperiodic signals; replacing it with a closed-form geodesic on the phase--amplitude cylinder eliminates these artifacts and converts each training pair into dense, geometry-consistent velocity supervision.1
• On zero-shot photoplethysmography and limited-support seismocardiography adaptation benchmarks, our method consistently outperforms interpolation baselines and matches or exceeds direct supervised prediction, reducing Hilbert Transform, $L2$, and Dynamic Time Warping distance by up to ${\sim}15%$ over the strongest competing baseline.1
• These results suggest that bridge geometry is a critical inductive bias for flow matching on oscillatory signal translation.1

Sources (1)

• [1]Cylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal Transformation
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 03:15 PM

  We introduce cylindrical geodesic flow matching for paired cardiovascular waveform translation.

  Paired translation between quasiperiodic physiological waveforms (i.e., recovering a target oscillatory signal from the source) is central to the interpretation of cardiovascular signals derived from wearables placed at different body locations.

Extractive summary: sentences quoted from the sources.