Reperio-rPPG: Relational Temporal Graph Neural Networks for Periodicity Learning in Remote Physiological Measurement
This work addresses a key limitation in non-invasive health monitoring for applications such as telemedicine and driver fatigue detection, though it appears incremental by building on existing rPPG methods.
The paper tackles the problem of insufficiently modeling periodicity in remote photoplethysmography (rPPG) for estimating vital signs like heart rate from facial videos, and the result is that Reperio-rPPG achieves state-of-the-art performance with robustness across motion and illumination conditions on benchmark datasets.
Remote photoplethysmography (rPPG) is an emerging contactless physiological sensing technique that leverages subtle color variations in facial videos to estimate vital signs such as heart rate and respiratory rate. This non-invasive method has gained traction across diverse domains, including telemedicine, affective computing, driver fatigue detection, and health monitoring, owing to its scalability and convenience. Despite significant progress in remote physiological signal measurement, a crucial characteristic - the intrinsic periodicity - has often been underexplored or insufficiently modeled in previous approaches, limiting their ability to capture fine-grained temporal dynamics under real-world conditions. To bridge this gap, we propose Reperio-rPPG, a novel framework that strategically integrates Relational Convolutional Networks with a Graph Transformer to effectively capture the periodic structure inherent in physiological signals. Additionally, recognizing the limited diversity of existing rPPG datasets, we further introduce a tailored CutMix augmentation to enhance the model's generalizability. Extensive experiments conducted on three widely used benchmark datasets - PURE, UBFC-rPPG, and MMPD - demonstrate that Reperio-rPPG not only achieves state-of-the-art performance but also exhibits remarkable robustness under various motion (e.g., stationary, rotation, talking, walking) and illumination conditions (e.g., nature, low LED, high LED). The code is publicly available at https://github.com/deconasser/Reperio-rPPG.