Saved in:
Bibliographic Details
Main Authors: Comas, Joaquim, Alomar, Antonia, Ruiz, Adria, Sukno, Federico
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.21519
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909274989395968
author Comas, Joaquim
Alomar, Antonia
Ruiz, Adria
Sukno, Federico
author_facet Comas, Joaquim
Alomar, Antonia
Ruiz, Adria
Sukno, Federico
contents In recent years, deep learning methods have shown impressive results for camera-based remote physiological signal estimation, clearly surpassing traditional methods. However, the performance and generalization ability of Deep Neural Networks heavily depends on rich training data truly representing different factors of variation encountered in real applications. Unfortunately, many current remote photoplethysmography (rPPG) datasets lack diversity, particularly in darker skin tones, leading to biased performance of existing rPPG approaches. To mitigate this bias, we introduce PhysFlow, a novel method for augmenting skin diversity in remote heart rate estimation using conditional normalizing flows. PhysFlow adopts end-to-end training optimization, enabling simultaneous training of supervised rPPG approaches on both original and generated data. Additionally, we condition our model using CIELAB color space skin features directly extracted from the facial videos without the need for skin-tone labels. We validate PhysFlow on publicly available datasets, UCLA-rPPG and MMPD, demonstrating reduced heart rate error, particularly in dark skin tones. Furthermore, we demonstrate its versatility and adaptability across different data-driven rPPG methods.
format Preprint
id arxiv_https___arxiv_org_abs_2407_21519
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PhysFlow: Skin tone transfer for remote heart rate estimation through conditional normalizing flows
Comas, Joaquim
Alomar, Antonia
Ruiz, Adria
Sukno, Federico
Computer Vision and Pattern Recognition
In recent years, deep learning methods have shown impressive results for camera-based remote physiological signal estimation, clearly surpassing traditional methods. However, the performance and generalization ability of Deep Neural Networks heavily depends on rich training data truly representing different factors of variation encountered in real applications. Unfortunately, many current remote photoplethysmography (rPPG) datasets lack diversity, particularly in darker skin tones, leading to biased performance of existing rPPG approaches. To mitigate this bias, we introduce PhysFlow, a novel method for augmenting skin diversity in remote heart rate estimation using conditional normalizing flows. PhysFlow adopts end-to-end training optimization, enabling simultaneous training of supervised rPPG approaches on both original and generated data. Additionally, we condition our model using CIELAB color space skin features directly extracted from the facial videos without the need for skin-tone labels. We validate PhysFlow on publicly available datasets, UCLA-rPPG and MMPD, demonstrating reduced heart rate error, particularly in dark skin tones. Furthermore, we demonstrate its versatility and adaptability across different data-driven rPPG methods.
title PhysFlow: Skin tone transfer for remote heart rate estimation through conditional normalizing flows
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.21519