PaperarXiv:2606.21436
Pixel Watch: Robust Heart Rate Sensing from Multipath PPG and On-Device Deep Learning Trained on 10,000 hours of Free-Living and Fitness Data
arXiv preprint (cs.HC) · in IEEE Sensors Letters, 2026
(opens in a new tab)Roggen, Daniel et al., "Pixel Watch: Robust Heart Rate Sensing from Multipath PPG and On-Device Deep Learning Trained on 10,000 hours of Free-Living and Fitness Data", arXiv:2606.21436, CC BY 4.0
TL;DR
The Pixel Watch 2 (PW2) is the first Google smartwatch to combine multipath photoplethysmography (PPG) with deep learning-based heart rate inference, designed to significantly improve sensing accuracy during motion-heavy activities. The device processes 10 optical channels using an on-device, 15-layer temporally dilated convolutional neural network (~300K parameters) to yield a 1 Hz heart rate output. Crucial to this model's performance was its training on a massive dataset comprising 10,000 hours of data from 962 participants, curated from a broader corpus of controlled and free-living activities.
- Form factor: wrist
Abstract
The Pixel Watch 2 (PW2) is the first Google smartwatch to combine multipath photoplethysmography (PPG) with deep learning-based heart rate inference, designed to significantly improve sensing accuracy during motion-heavy activities. The device processes 10 optical channels using an on-device, 15-layer temporally dilated convolutional neural network (~300K parameters) to yield a 1 Hz heart rate output. Crucial to this model's performance was its training on a massive dataset comprising 10,000 hours of data from 962 participants, curated from a broader corpus of controlled and free-living activities. We evaluated the PW2's sensing performance across two independent validation sets: an in-house fitness dataset (229 participants, 250 hours) and an external free-living dataset (27 participants, 1000+ hours). The system achieved 95% Limits of Agreement of -10.34 to 8.66 BPM during exercise and -6.57 to 7.48 BPM during free-living activities, demonstrating substantially tighter error margins than previous Google devices. Finally, we discuss key design lessons, emphasizing that large-scale deep learning was instrumental in fully leveraging multipath PPG hardware over traditional signal processing approaches.
Verbatim from arXiv (opens in a new tab) · arXiv metadata (abstracts are released under CC0)
Results on ChatPPG leaderboards
All leaderboardsNo results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.
Tasks & signals
Tasks
Signals
Keywords
How it works
- Wavelengths
- green, red, IR
Cite this paper
APA
Roggen, D., Walker, M., Patel, Y., Tailor, S., Spathis, D., Wimmer, M., et al. (2026). Pixel Watch: Robust Heart Rate Sensing from Multipath PPG and On-Device Deep Learning Trained on 10,000 hours of Free-Living and Fitness Data. arXiv preprint · in IEEE Sensors Letters, 2026. https://doi.org/10.1109/LSENS.2026.3694237
BibTeX
@misc{roggen2026pixel,
title = {{Pixel Watch: Robust Heart Rate Sensing from Multipath PPG and On-Device Deep Learning Trained on 10,000 hours of Free-Living and Fitness Data}},
author = {Roggen, Daniel and Walker, Megan and Patel, Yojan and Tailor, Shyam and Spathis, Dimitris and Wimmer, Matt and others},
year = {2026},
howpublished = {arXiv preprint · in IEEE Sensors Letters, 2026},
doi = {10.1109/LSENS.2026.3694237},
eprint = {2606.21436},
archivePrefix = {arXiv}
}Built from the hub record. Check it against the publisher before submitting.
Added to the ChatPPG research hub
