Reperio-rPPG: Relational Temporal Graph Neural Networks for Periodicity Learning in Remote Physiological Measurement

TL;DR

Reperio-rPPG introduces a novel graph neural network framework that effectively captures the periodic nature of physiological signals in remote photoplethysmography, achieving state-of-the-art results across multiple datasets and conditions.

Contribution

The paper presents Reperio-rPPG, a new relational temporal graph neural network that models periodicity in rPPG signals and introduces a data augmentation technique to improve robustness and generalization.

Findings

Achieves state-of-the-art performance on PURE, UBFC-rPPG, and MMPD datasets.

Demonstrates robustness under various motion and lighting conditions.

Outperforms existing methods in accuracy and stability.

Abstract

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.