FreqPhys: Repurposing Implicit Physiological Frequency Prior for Robust Remote Photoplethysmography

TL;DR

FreqPhys introduces a frequency-guided framework for remote photoplethysmography that explicitly leverages physiological frequency priors, significantly improving robustness against motion and lighting artifacts.

Contribution

It proposes a novel frequency-aware rPPG method combining spectral filtering, modulation, and diffusion processes to enhance signal recovery under challenging conditions.

Findings

Outperforms state-of-the-art methods on six benchmarks.

Effectively suppresses motion artifacts and illumination fluctuations.

Enhances pulse-related frequency component extraction.

Abstract

Remote photoplethysmography (rPPG) enables contactless physiological monitoring by capturing subtle skin-color variations from facial videos. However, most existing methods predominantly rely on time-domain modeling, making them vulnerable to motion artifacts and illumination fluctuations, where weak physiological clues are easily overwhelmed by noise. To address these challenges, we propose FreqPhys, a frequency-guided rPPG framework that explicitly leverages physiological frequency priors for robust signal recovery. Specifically, FreqPhys first applies a Physiological Bandpass Filtering module to suppress out-of-band interference, and then performs Physiological Spectrum Modulation together with adaptive spectral selection to emphasize pulse-related frequency components while suppress residual in-band noise. A Cross-domain Representation Learning module further fuses these spectral priors with deep time-domain features to capture informative spatial--temporal dependencies. Finally, a frequency-aware conditional diffusion process progressively reconstructs high-fidelity rPPG signals. Extensive experiments on six benchmarks demonstrate that FreqPhys yields significant improvements over state-of-the-art approaches, particularly under challenging motion conditions. It highlights the importance of explicitly modeling physiological frequency priors. The source code will be released.