Memory-efficient Low-latency Remote Photoplethysmography through Temporal-Spatial State Space Duality

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Kegang, Tang, Jiankai, Fan, Yuxuan, Ji, Jiatong, Shi, Yuanchun, Wang, Yuntao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909568071630848
author Wang, Kegang
Tang, Jiankai
Fan, Yuxuan
Ji, Jiatong
Shi, Yuanchun
Wang, Yuntao
author_facet Wang, Kegang
Tang, Jiankai
Fan, Yuxuan
Ji, Jiatong
Shi, Yuanchun
Wang, Yuntao
contents Remote photoplethysmography (rPPG), enabling non-contact physiological monitoring through facial light reflection analysis, faces critical computational bottlenecks as deep learning introduces performance gains at the cost of prohibitive resource demands. This paper proposes ME-rPPG, a memory-efficient algorithm built on temporal-spatial state space duality, which resolves the trilemma of model scalability, cross-dataset generalization, and real-time constraints. Leveraging a transferable state space, ME-rPPG efficiently captures subtle periodic variations across facial frames while maintaining minimal computational overhead, enabling training on extended video sequences and supporting low-latency inference. Achieving cross-dataset MAEs of 5.38 (MMPD), 0.70 (VitalVideo), and 0.25 (PURE), ME-rPPG outperforms all baselines with improvements ranging from 21.3% to 60.2%. Our solution enables real-time inference with only 3.6 MB memory usage and 9.46 ms latency -- surpassing existing methods by 19.5%-49.7% accuracy and 43.2% user satisfaction gains in real-world deployments. The code and demos are released for reproducibility on https://health-hci-group.github.io/ME-rPPG-demo/.
format Preprint
id arxiv_https___arxiv_org_abs_2504_01774
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Memory-efficient Low-latency Remote Photoplethysmography through Temporal-Spatial State Space Duality
Wang, Kegang
Tang, Jiankai
Fan, Yuxuan
Ji, Jiatong
Shi, Yuanchun
Wang, Yuntao
Computer Vision and Pattern Recognition
Remote photoplethysmography (rPPG), enabling non-contact physiological monitoring through facial light reflection analysis, faces critical computational bottlenecks as deep learning introduces performance gains at the cost of prohibitive resource demands. This paper proposes ME-rPPG, a memory-efficient algorithm built on temporal-spatial state space duality, which resolves the trilemma of model scalability, cross-dataset generalization, and real-time constraints. Leveraging a transferable state space, ME-rPPG efficiently captures subtle periodic variations across facial frames while maintaining minimal computational overhead, enabling training on extended video sequences and supporting low-latency inference. Achieving cross-dataset MAEs of 5.38 (MMPD), 0.70 (VitalVideo), and 0.25 (PURE), ME-rPPG outperforms all baselines with improvements ranging from 21.3% to 60.2%. Our solution enables real-time inference with only 3.6 MB memory usage and 9.46 ms latency -- surpassing existing methods by 19.5%-49.7% accuracy and 43.2% user satisfaction gains in real-world deployments. The code and demos are released for reproducibility on https://health-hci-group.github.io/ME-rPPG-demo/.
title Memory-efficient Low-latency Remote Photoplethysmography through Temporal-Spatial State Space Duality
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.01774