BeatFlow-ECG: Rectified Flow for ECG Reconstruction from Indirect Wearable Signals

Anonymous (ICLR 2027 double-blind)

Summary

Conditional rectified-flow model reconstructing single-channel ECG from synchronized PPG + inertial signals (conv encoder–decoder, transformer bottleneck, explicit flow-time conditioning). Motion enters via IMU-derived conditioning features, motion-dependent loss weighting and an easy-to-hard curriculum. Leave-one-subject-out on PPG-DaLiA and WESAD: best among deterministic, adversarial and diffusion baselines on all waveform and beat-timing metrics — Pearson r 0.983 / 0.986, R-peak F1 0.946 / 0.955 (DaLiA / WESAD); vs Conditional DDPM-1D, L1 error 0.085→0.062 (DaLiA) and 0.074→0.055 (WESAD).