RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement
Bochao Zou, Zizheng Guo, Xiaocheng Hu, Huimin Ma
Abstract
Remote photoplethysmography (rPPG) is a method for non-contact measurement of physiological signals from facial videos, holding great potential in various applications such as healthcare, affective computing, and anti-spoofing. Existing deep learning methods struggle to address two core issues of rPPG simultaneously: understanding the periodic pattern of rPPG among long contexts and addressing large spatiotemporal redundancy in video segments. These represent a trade-off between computational complexity and the ability to capture long-range dependencies. In this paper, we introduce RhythmMamba, a state space model-based method that captures long-range dependencies while maintaining linear complexity. By viewing rPPG as a time series task through the proposed frame stem, the periodic variations in pulse waves are modeled as state transitions. Additionally, we design multi-temporal constraint and frequency domain feed-forward, both aligned with the characteristics of rPPG time series, to improve the learning capacity of Mamba for rPPG signals. Extensive experiments show that RhythmMamba achieves state-of-the-art performance with 319% throughput and 23% peak GPU memory.
BibTeX
@article{Zou_Guo_Hu_Ma_2025, title={RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/33204}, DOI={10.1609/aaai.v39i10.33204}, abstractNote={Remote photoplethysmography (rPPG) is a method for non-contact measurement of physiological signals from facial videos, holding great potential in various applications such as healthcare, affective computing, and anti-spoofing. Existing deep learning methods struggle to address two core issues of rPPG simultaneously: understanding the periodic pattern of rPPG among long contexts and addressing large spatiotemporal redundancy in video segments. These represent a trade-off between computational complexity and the ability to capture long-range dependencies. In this paper, we introduce RhythmMamba, a state space model-based method that captures long-range dependencies while maintaining linear complexity. By viewing rPPG as a time series task through the proposed frame stem, the periodic variations in pulse waves are modeled as state transitions. Additionally, we design multi-temporal constraint and frequency domain feed-forward, both aligned with the characteristics of rPPG time series, to improve the learning capacity of Mamba for rPPG signals. Extensive experiments show that RhythmMamba achieves state-of-the-art performance with 319% throughput and 23% peak GPU memory.}, number={10}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Zou, Bochao and Guo, Zizheng and Hu, Xiaocheng and Ma, Huimin}, year={2025}, month={Apr.}, pages={11077-11085} }