# M3PD Dataset: Dual-view Photoplethysmography (PPG) Using Front-and-rear Cameras of Smartphones in Lab and Clinical Settings

arXiv: https://arxiv.org/abs/2511.02349 · HTML: https://mlsanity.com/paper/2511.02349/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 50 references that are in the map.
- First posted on arXiv 4 Nov 2025.

## Builds on (most cited first, 25 of 25)

- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Multimodal Transformer for Unaligned Multimodal Language Sequences](https://mlsanity.com/paper/1906.00295/) (2019)
- [DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks](https://mlsanity.com/paper/1805.07888/) (2018)
- [Remote Photoplethysmograph Signal Measurement from Facial Videos Using Spatio-Temporal Networks](https://mlsanity.com/paper/1905.02419/) (2019)
- [PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer](https://mlsanity.com/paper/2111.12082/) (2021)
- [FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with Mamba](https://mlsanity.com/paper/2404.09498/) (2024)
- [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)
- [MMPD: Multi-Domain Mobile Video Physiology Dataset](https://mlsanity.com/paper/2302.03840/) (2023)
- [Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition](https://mlsanity.com/paper/2008.09412/) (2020)
- [ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs](https://mlsanity.com/paper/1512.05193/) (2015)
- [RhythmFormer: Extracting Patterned rPPG Signals based on Periodic Sparse Attention](https://mlsanity.com/paper/2402.12788/) (2024)
- [Face2PPG: An unsupervised pipeline for blood volume pulse extraction from faces](https://mlsanity.com/paper/2202.04101/) (2022)
- [U2Net: A General Framework with Spatial-Spectral-Integrated Double U-Net for Image Fusion](https://mlsanity.com/paper/2212.06466/) (2022)
- [Spiking-PhysFormer: Camera-Based Remote Photoplethysmography with Parallel Spike-driven Transformer](https://mlsanity.com/paper/2402.04798/) (2024)
- [PhysMamba: Efficient Remote Physiological Measurement with SlowFast Temporal Difference Mamba](https://mlsanity.com/paper/2409.12031/) (2024)
- [Camera-Based HRV Prediction for Remote Learning Environments](https://mlsanity.com/paper/2305.04161/) (2023)
- [Smartphone Camera Oximetry in an Induced Hypoxemia Study](https://mlsanity.com/paper/2104.00038/) (2021)
- [PhysDrive: A Multimodal Remote Physiological Measurement Dataset for In-vehicle Driver Monitoring](https://mlsanity.com/paper/2507.19172/) (2025)
- [Summit Vitals: Multi-Camera and Multi-Signal Biosensing at High Altitudes](https://mlsanity.com/paper/2409.19223/) (2024)
- [A Plug-and-Play Temporal Normalization Module for Robust Remote Photoplethysmography](https://mlsanity.com/paper/2411.15283/) (2024)
- [Camera-Based Remote Physiology Sensing for Hundreds of Subjects Across Skin Tones](https://mlsanity.com/paper/2404.05003/) (2024)
- [MoRAL: Motion-aware Multi-Frame 4D Radar and LiDAR Fusion for Robust 3D Object Detection](https://mlsanity.com/paper/2505.09422/) (2025)
- [Non-Contact Health Monitoring During Daily Personal Care Routines](https://mlsanity.com/paper/2506.09718/) (2025)
- [UbiHR: Resource-efficient Long-range Heart Rate Sensing on Ubiquitous Devices](https://mlsanity.com/paper/2410.19279/) (2024)

## Built on by (most cited first, 1 of 1)

- [FacePhys: State of the Heart Learning](https://mlsanity.com/paper/2512.06275/) (2025)

## Abstract (arXiv)

Portable physiological monitoring is essential for early detection and management of cardiovascular disease, but current methods often require specialized equipment that limits accessibility or impose impractical postures that patients cannot maintain. Video-based photoplethysmography on smartphones offers a convenient noninvasive alternative, yet it still faces reliability challenges caused by motion artifacts, lighting variations, and single-view constraints. Few studies have demonstrated reliable application to cardiovascular patients, and no widely used open datasets exist for cross-device accuracy. To address these limitations, we introduce the M3PD dataset, the first publicly available dual-view mobile photoplethysmography dataset, comprising synchronized facial and fingertip videos captured simultaneously via front and rear smartphone cameras from 60 participants (including 47 cardiovascular patients). Building on this dual-view setting, we further propose F3Mamba, which fuses the facial and fingertip views through Mamba-based temporal modeling. The model reduces heart-rate error by 21.9 to 30.2 percent over existing single-view baselines while improving robustness in challenging real-world scenarios. Data and code: https://github.com/Health-HCI-Group/F3Mamba.