# How Suboptimal is Training rPPG Models with Videos and Targets from Different Body Sites?

arXiv: https://arxiv.org/abs/2403.10582 · HTML: https://mlsanity.com/paper/2403.10582/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 42 references that are in the map.
- First posted on arXiv 15 Mar 2024.

## Builds on (most cited first, 11 of 11)

- [DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks](https://mlsanity.com/paper/1805.07888/) (2018)
- [Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement](https://mlsanity.com/paper/2006.03790/) (2020)
- [PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer](https://mlsanity.com/paper/2111.12082/) (2021)
- [Remote Heart Rate Measurement from Highly Compressed Facial Videos: an End-to-end Deep Learning Solution with Video Enhancement](https://mlsanity.com/paper/1907.11921/) (2019)
- [The Way to my Heart is through Contrastive Learning: Remote Photoplethysmography from Unlabelled Video](https://mlsanity.com/paper/2111.09748/) (2021)
- [rPPG-Toolbox: Deep Remote PPG Toolbox](https://mlsanity.com/paper/2210.00716/) (2022)
- [VIPL-HR: A Multi-modal Database for Pulse Estimation from Less-constrained Face Video](https://mlsanity.com/paper/1810.04927/) (2018)
- [Camera Measurement of Physiological Vital Signs](https://mlsanity.com/paper/2111.11547/) (2021)
- [SimPer: Simple Self-Supervised Learning of Periodic Targets](https://mlsanity.com/paper/2210.03115/) (2022)
- [Video-based sympathetic arousal assessment via peripheral blood flow estimation](https://mlsanity.com/paper/2311.06930/) (2023)
- [Full-Body Cardiovascular Sensing with Remote Photoplethysmography](https://mlsanity.com/paper/2303.09638/) (2023)

## Built on by (most cited first, 9 of 9)

- [egoPPG: Heart Rate Estimation from Eye-Tracking Cameras in Egocentric Systems to Benefit Downstream Vision Tasks](https://mlsanity.com/paper/2502.20879/) (2025)
- [SympCam: Remote Optical Measurement of Sympathetic Arousal](https://mlsanity.com/paper/2410.20552/) (2024)
- [egoEMOTION: Egocentric Vision and Physiological Signals for Emotion and Personality Recognition in Real-World Tasks](https://mlsanity.com/paper/2510.22129/) (2025)
- [Align the GAP: Prior-based Unified Multi-Task Remote Physiological Measurement Framework For Domain Generalization and Personalization](https://mlsanity.com/paper/2506.16160/) (2025)
- [3D Blood Pulsation Maps](https://mlsanity.com/paper/2512.10517/) (2025)
- [Template Collapse and Information-Theoretic Limits in Camera rPPG Pulse Morphology Restoration](https://mlsanity.com/paper/2606.03802/) (2026)
- [StreamPPG: Low-Latency rPPG Estimation via Consistent Privileged Learning](https://mlsanity.com/paper/2606.23186/) (2026)
- [SkillSpotter: Pose-Aware Multi-View Skilled Action Detection and Grading in Ego-Exo Videos](https://mlsanity.com/paper/2606.31127/) (2026)
- [Beyond Contact Sensors: Deep learning with Pseudo-Labeling for remote Photoplethysmography](https://mlsanity.com/paper/2609.10026/) (2026)

## Abstract (arXiv)

Remote camera measurement of the blood volume pulse via photoplethysmography (rPPG) is a compelling technology for scalable, low-cost, and accessible assessment of cardiovascular information. Neural networks currently provide the state-of-the-art for this task and supervised training or fine-tuning is an important step in creating these models. However, most current models are trained on facial videos using contact PPG measurements from the fingertip as targets/ labels. One of the reasons for this is that few public datasets to date have incorporated contact PPG measurements from the face. Yet there is copious evidence that the PPG signals at different sites on the body have very different morphological features. Is training a facial video rPPG model using contact measurements from another site on the body suboptimal? Using a recently released unique dataset with synchronized contact PPG and video measurements from both the hand and face, we can provide precise and quantitative answers to this question. We obtain up to 40 % lower mean squared errors between the waveforms of the predicted and the ground truth PPG signals using state-of-the-art neural models when using PPG signals from the forehead compared to using PPG signals from the fingertip. We also show qualitatively that the neural models learn to predict the morphology of the ground truth PPG signal better when trained on the forehead PPG signals. However, while models trained from the forehead PPG produce a more faithful waveform, models trained from a finger PPG do still learn the dominant frequency (i.e., the heart rate) well.