SFDA-rPPG: Source-Free Domain Adaptive Remote Physiological Measurement with Spatio-Temporal Consistency

TL;DR

This paper introduces SFDA-rPPG, a novel source-free domain adaptation framework for remote physiological measurement using facial videos, which effectively aligns spectral features across domains without source data access.

Contribution

It proposes the first source-free domain adaptation method for rPPG, utilizing a three-branch network and a frequency-domain Wasserstein distance loss for spectral alignment.

Findings

Effective cross-domain adaptation demonstrated in experiments

FWD loss improves spectral distribution alignment

Source-free approach preserves privacy and data security

Abstract

Remote Photoplethysmography (rPPG) is a non-contact method that uses facial video to predict changes in blood volume, enabling physiological metrics measurement. Traditional rPPG models often struggle with poor generalization capacity in unseen domains. Current solutions to this problem is to improve its generalization in the target domain through Domain Generalization (DG) or Domain Adaptation (DA). However, both traditional methods require access to both source domain data and target domain data, which cannot be implemented in scenarios with limited access to source data, and another issue is the privacy of accessing source domain data. In this paper, we propose the first Source-free Domain Adaptation benchmark for rPPG measurement (SFDA-rPPG), which overcomes these limitations by enabling effective domain adaptation without access to source domain data. Our framework incorporates a Three-Branch Spatio-Temporal Consistency Network (TSTC-Net) to enhance feature consistency across domains. Furthermore, we propose a new rPPG distribution alignment loss based on the Frequency-domain Wasserstein Distance (FWD), which leverages optimal transport to align power spectrum distributions across domains effectively and further enforces the alignment of the three branches. Extensive cross-domain experiments and ablation studies demonstrate the effectiveness of our proposed method in source-free domain adaptation settings. Our findings highlight the significant contribution of the proposed FWD loss for distributional alignment, providing a valuable reference for future research and applications. The source code is available at https://github.com/XieYiping66/SFDA-rPPG