PhysMamba: State Space Duality Model for Remote Physiological Measurement
This work addresses challenges in non-contact health monitoring for applications like medical assistance and anti-face spoofing, representing a novel method for a known bottleneck.
The paper tackles the problem of remote physiological measurement from facial videos, which is limited by motion artifacts and noise, by proposing PhysMamba, a dual-pathway model that integrates state space models with attention mechanisms, achieving superior accuracy and generalization on benchmark datasets.
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.