ChatPPG.
Join free
Model

PhysNet

spatio-temporal 3D-CNN for remote PPG

Code Cite
UnconfirmedCatalog paper date: 2019Source
GitHub starsView on GitHub (opens in a new tab)

Activity counts measure attention, not model quality. Missing counts are unknown. Publication status follows the linked source; a listed venue alone does not confirm peer review.

PhysNet is a spatio-temporal 3D convolutional network for remote PPG (BMVC 2019; arXiv:1905.02419). Open implementations and pretrained checkpoints appear in the UW rPPG-Toolbox and the open-rppg zoo.

Form factor
camera_rppg
Openness
Open
Year
2019
Published
arXiv:1905.02419

arXiv: 1905.02419

Code

github.com/ubicomplab/rPPG-Toolbox · open-rppg PhysNet.*.pure/rlap

At a glance
Type
Task model
Modalities
Not reported
Form factor
Camera rPPG
Parameters
Not reported
Architecture
Not reported
Venue
Not reported
Year
2019
arXiv
1905.02419 (opens in a new tab)
DOI
Not reported
Code
Not reported
Weights
Not reported
Licence
Not reported
Caveats
Not reported
Datasets
Not reported
Added
Not reported
Updated
Oct 24, 2026

Abstract

Recent studies demonstrated that the average heart rate (HR) can be measured from facial videos based on non-contact remote photoplethysmography (rPPG). However for many medical applications (e.g., atrial fibrillation (AF) detection) knowing only the average HR is not sufficient, and measuring precise rPPG signals from face for heart rate variability (HRV) analysis is needed. Here we propose an rPPG measurement method, which is the first work to use deep spatio-temporal networks for reconstructing precise rPPG signals from raw facial videos. With the constraint of trend-consistency with ground truth pulse curves, our method is able to recover rPPG signals with accurate pulse peaks. Comprehensive experiments are conducted on two benchmark datasets, and results demonstrate that our method can achieve superior performance on both HR and HRV levels comparing to the state-of-the-art methods. We also achieve promising results of using reconstructed rPPG signals for AF detection and emotion recognition.

Verbatim fromarXiv· arXiv metadata (abstracts are released under CC0)

PhysNet: ChatPPG research summary card

How it works

Inputs
PhysNet
Outputs / tasks
Downstream tasks
Approach
rppg · model · physnet

Datasets

No public datasets linked yet.

Cite

APA

PhysNet. (2019). arXiv. https://arxiv.org/abs/1905.02419

BibTeX

@misc{physnet2019physnet,
  title         = {{PhysNet}},
  year          = {2019},
  eprint        = {1905.02419},
  archivePrefix = {arXiv}
}

Built from the hub record. Check it against the publisher before submitting.

History

  1. Record updated

Same tasks, data and authors