VitalLens 2.0: High-Fidelity rPPG for Heart Rate Variability Estimation from Face Video

TL;DR

VitalLens 2.0 is a deep learning model that significantly improves the accuracy of remote photoplethysmography (rPPG) for estimating heart rate, respiratory rate, and heart rate variability from face videos, using enhanced architecture and diverse training data.

Contribution

The paper introduces VitalLens 2.0, a novel high-fidelity rPPG model with improved architecture and a large, diverse dataset, achieving state-of-the-art accuracy in physiological signal estimation.

Findings

Achieves MAE of 1.57 bpm for HR

Achieves MAE of 1.08 bpm for RR

Outperforms previous methods in HRV metrics

Abstract

This report introduces VitalLens 2.0, a new deep learning model for estimating physiological signals from face video. This new model demonstrates a significant leap in accuracy for remote photoplethysmography (rPPG), enabling the robust estimation of not only heart rate (HR) and respiratory rate (RR) but also Heart Rate Variability (HRV) metrics. This advance is achieved through a combination of a new model architecture and a substantial increase in the size and diversity of our training data, now totaling 1,413 unique individuals. We evaluate VitalLens 2.0 on a new, combined test set of 422 unique individuals from four public and private datasets. When averaging results by individual, VitalLens 2.0 achieves a Mean Absolute Error (MAE) of 1.57 bpm for HR, 1.08 bpm for RR, 10.18 ms for HRV-SDNN, and 16.45 ms for HRV-RMSSD. These results represent a new state-of-the-art, significantly outperforming previous methods. This model is now available to developers via the VitalLens API at https://rouast.com/api.