3D Blood Pulsation Maps

TL;DR

This paper introduces Pulse3DFace, a novel dataset of 3D blood pulsation maps from multiple viewpoints, enabling advanced research in remote pulse estimation and illumination-invariant analysis.

Contribution

The creation of the first comprehensive 3D blood pulsation map dataset with multi-view videos, reference measurements, and processed maps for physiological and computational research.

Findings

Dataset captures physiologically meaningful features.

Maps are consistent across different illumination conditions.

Enables development of multi-view and illumination-robust pulse estimation methods.

Abstract

We present Pulse3DFace, the first dataset of its kind for estimating 3D blood pulsation maps. These maps can be used to develop models of dynamic facial blood pulsation, enabling the creation of synthetic video data to improve and validate remote pulse estimation methods via photoplethysmography imaging. Additionally, the dataset facilitates research into novel multi-view-based approaches for mitigating illumination effects in blood pulsation analysis. Pulse3DFace consists of raw videos from 15 subjects recorded at 30 Hz with an RGB camera from 23 viewpoints, blood pulse reference measurements, and facial 3D scans generated using monocular structure-from-motion techniques. It also includes processed 3D pulsation maps compatible with the texture space of the 3D head model FLAME. These maps provide signal-to-noise ratio, local pulse amplitude, phase information, and supplementary data. We offer a comprehensive evaluation of the dataset's illumination conditions, map consistency, and its ability to capture physiologically meaningful features in the facial and neck skin regions.