# Face2PPG: An unsupervised pipeline for blood volume pulse extraction from faces arXiv: https://arxiv.org/abs/2202.04101 ยท HTML: https://mlsanity.com/paper/2202.04101/ ## Key facts - Cited by 22 papers in the map (data through 14 Oct 2026). - Builds on 14 of its 97 references that are in the map. - First posted on arXiv 8 Feb 2022. ## Builds on (most cited first, 14 of 14) - [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015) - [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016) - [DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks](https://mlsanity.com/paper/1805.07888/) (2018) - [RhythmNet: End-to-end Heart Rate Estimation from Face via Spatial-temporal Representation](https://mlsanity.com/paper/1910.11515/) (2019) - [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) - [PulseGAN: Learning to generate realistic pulse waveforms in remote photoplethysmography](https://mlsanity.com/paper/2006.02699/) (2020) - [Meta-rPPG: Remote Heart Rate Estimation Using a Transductive Meta-Learner](https://mlsanity.com/paper/2007.06786/) (2020) - [A Reproducible Study on Remote Heart Rate Measurement](https://mlsanity.com/paper/1709.00962/) (2017) - [Deep Alignment Network: A convolutional neural network for robust face alignment](https://mlsanity.com/paper/1706.01789/) (2017) - [AutoHR: A Strong End-to-end Baseline for Remote Heart Rate Measurement with Neural Searching](https://mlsanity.com/paper/2004.12292/) (2020) - [Analysis of CNN-based remote-PPG to understand limitations and sensitivities](https://mlsanity.com/paper/1911.02736/) (2019) - [Real-time Webcam Heart-Rate and Variability Estimation with Clean Ground Truth for Evaluation](https://mlsanity.com/paper/2012.15846/) (2020) - [Pulse rate estimation using imaging photoplethysmography: generic framework and comparison of methods on a publicly available dataset](https://mlsanity.com/paper/1710.08369/) (2017) ## Built on by (most cited first, 22 of 22) - [RhythmFormer: Extracting Patterned rPPG Signals based on Periodic Sparse Attention](https://mlsanity.com/paper/2402.12788/) (2024) - [RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement](https://mlsanity.com/paper/2404.06483/) (2024) - [Depression Recognition using Remote Photoplethysmography from Facial Videos](https://mlsanity.com/paper/2206.04399/) (2022) - [Orientation-conditioned Facial Texture Mapping for Video-based Facial Remote Photoplethysmography Estimation](https://mlsanity.com/paper/2404.09378/) (2024) - [Non-Contact Heart Rate Measurement from Deteriorated Videos](https://mlsanity.com/paper/2304.14789/) (2023) - [OMuSense-23: A Multimodal Dataset for Contactless Breathing Pattern Recognition and Biometric Analysis](https://mlsanity.com/paper/2407.06137/) (2024) - [Evaluation of Video-Based rPPG in Challenging Environments: Artifact Mitigation and Network Resilience](https://mlsanity.com/paper/2405.01230/) (2024) - [Feasibility of Detecting Cognitive Impairment and Psychological Well-being among Older Adults Using Facial, Acoustic, Linguistic, and Cardiovascular Patterns Derived from Remote Conversations](https://mlsanity.com/paper/2412.14194/) (2024) - [Remote Bio-Sensing: Open Source Benchmark Framework for Fair Evaluation of rPPG](https://mlsanity.com/paper/2307.12644/) (2023) - [SkinMap: Weighted Full-Body Skin Segmentation for Robust Remote Photoplethysmography](https://mlsanity.com/paper/2510.05296/) (2025) - [M3PD Dataset: Dual-view Photoplethysmography (PPG) Using Front-and-rear Cameras of Smartphones in Lab and Clinical Settings](https://mlsanity.com/paper/2511.02349/) (2025) - [Quality-Aware Framework for Video-Derived Respiratory Signals](https://mlsanity.com/paper/2512.14093/) (2025) - [KDPhys: An Attention Guided 3D to 2D Knowledge Distillation for Real-time Video-Based Physiological Measurement](https://mlsanity.com/paper/2601.00714/) (2026) - [Thermal Imaging for Contactless Cardiorespiratory and Sudomotor Response Monitoring](https://mlsanity.com/paper/2602.12361/) (2026) - [EMPD: An Event-based Multimodal Physiological Dataset for Remote Pulse Wave Detection](https://mlsanity.com/paper/2603.26699/) (2026) - [rPPG-VQA: A Video Quality Assessment Framework for Unsupervised rPPG Training](https://mlsanity.com/paper/2604.11156/) (2026) - [Facial Kinship Verification from remote photoplethysmography](https://mlsanity.com/paper/2309.08006/) (2023) - [Multi-objective Feature Selection in Remote Health Monitoring Applications](https://mlsanity.com/paper/2401.05538/) (2024) - [Adaptive Parameter Optimization for Robust Remote Photoplethysmography](https://mlsanity.com/paper/2511.21903/) (2025) - [Facial Spatiotemporal Graphs: Leveraging the 3D Facial Surface for Remote Physiological Measurement](https://mlsanity.com/paper/2601.13724/) (2026) - [Video-based Heart Rate Estimation with Angle-guided ROI Optimization and Graph Signal Denoising](https://mlsanity.com/paper/2604.11395/) (2026) - [StreamPPG: Low-Latency rPPG Estimation via Consistent Privileged Learning](https://mlsanity.com/paper/2606.23186/) (2026) ## Abstract (arXiv) Photoplethysmography (PPG) signals have become a key technology in many fields, such as medicine, well-being, or sports. Our work proposes a set of pipelines to extract remote PPG signals (rPPG) from the face robustly, reliably, and configurable. We identify and evaluate the possible choices in the critical steps of unsupervised rPPG methodologies. We assess a state-of-the-art processing pipeline in six different datasets, incorporating important corrections in the methodology that ensure reproducible and fair comparisons. In addition, we extend the pipeline by proposing three novel ideas; 1) a new method to stabilize the detected face based on a rigid mesh normalization; 2) a new method to dynamically select the different regions in the face that provide the best raw signals, and 3) a new RGB to rPPG transformation method, called Orthogonal Matrix Image Transformation (OMIT) based on QR decomposition, that increases robustness against compression artifacts. We show that all three changes introduce noticeable improvements in retrieving rPPG signals from faces, obtaining state-of-the-art results compared with unsupervised, non-learning-based methodologies and, in some databases, very close to supervised, learning-based methods. We perform a comparative study to quantify the contribution of each proposed idea. In addition, we depict a series of observations that could help in future implementations.