PhysMamba: State Space Duality Model for Remote Physiological Measurement

TL;DR

PhysMamba introduces a dual-pathway time-frequency model integrating state space and attention mechanisms, significantly improving remote physiological measurement accuracy and robustness in challenging real-world conditions.

Contribution

It is the first to combine state space models with attention mechanisms in a dual-branch framework for remote physiological signal extraction.

Findings

Outperforms existing methods on multiple datasets

Achieves higher accuracy and robustness in noisy conditions

Demonstrates potential for real-time remote health monitoring

Abstract

Remote Photoplethysmography (rPPG) enables non-contact physiological signal extraction from facial videos, offering applications in psychological state analysis, medical assistance, and anti-face spoofing. However, challenges such as motion artifacts, lighting variations, and noise limit its real-world applicability. To address these issues, we propose PhysMamba, a novel dual-pathway time-frequency interaction model based on Synergistic State Space Duality (SSSD), which for the first time integrates state space models with attention mechanisms in a dual-branch framework. Combined with a Multi-Scale Query (MQ) mechanism, PhysMamba achieves efficient information exchange and enhanced feature representation, ensuring robustness under noisy and dynamic conditions. Experiments on PURE, UBFC-rPPG, and MMPD datasets demonstrate that PhysMamba outperforms state-of-the-art methods, offering superior accuracy and generalization. This work lays a strong foundation for practical applications in non-contact health monitoring, including real-time remote patient care.