HOT: Harmonic-Constrained Optimal Transport for Remote Photoplethysmography Domain Adaptation

TL;DR

This paper introduces frequency domain adaptation and harmonic-constrained optimal transport to improve the robustness of remote photoplethysmography models against appearance variations across different datasets.

Contribution

It proposes a novel framework combining FDA and HOT to enhance cross-dataset generalization in rPPG by modeling appearance invariance and physiologically consistent alignment.

Findings

FDA improves invariance to appearance variations.

HOT leverages cardiac harmonic properties for better alignment.

Framework enhances cross-dataset robustness of rPPG models.

Abstract

Remote photoplethysmography (rPPG) enables non-contact physiological measurement from facial videos; however, its practical deployment is often hindered by substantial performance degradation under domain shift. While recent deep learning-based rPPG methods have achieved strong performance on individual datasets, they frequently overfit to appearance-related factors, such as illumination, camera characteristics, and color response, that vary significantly across domains. To address this limitation, we introduce frequency domain adaptation (FDA) as a principled strategy for modeling appearance variation in rPPG. By transferring low-frequency spectral components that encode domain-dependent appearance characteristics, FDA encourages rPPG models to learn invariance to appearance variations while retaining cardiac-induced signals. To further support physiologically consistent alignment under such appearance variation, we propose Harmonic-Constrained Optimal Transport (HOT), which leverages the harmonic property of cardiac signals to guide alignment between original and FDA-transferred representations. Extensive cross-dataset experiments demonstrate that the proposed FDA and HOT framework effectively enhances the robustness and generalization of rPPG models across diverse datasets.