Remote Photoplethysmography Based on a Skin Reflection Exponential Model

Facial video–based remote photoplethysmography (rPPG) estimates physiological signals from subtle spatiotemporal variations in facial videos, but remains vulnerable to head motion, illumination changes, and environmental perturbations. Existing methods mainly distinguish rPPG-related variations from motion and lighting artifacts at the signal or feature level, while largely neglecting the optical reflection properties of human skin. In this work, we formulate a skin reflection exponential model to describe the nonlinear relationship among skin reflectance, illumination, motion-induced variations, and blood-volume changes. Guided by this model, we propose a physically inspired rPPG estimation framework that explicitly incorporates skin reflectance priors into signal extraction. Given a facial video, facial keypoints are first detected and encoded to represent motion dynamics, while illumination-related features and candidate rPPG representations are jointly modeled under the proposed exponential formulation. By constraining rPPG estimation with skin-reflection physics, the framework improves separation of physiological components from motion and illumination disturbances. Experiments demonstrate improved robustness under challenging conditions.