EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Noise-resilient spatial–channel refinement for robust remote photoplethysmography

Xianwei Zhang, Feng Qiao, Qiaochu Zang, Zhe Chen, Xiaoting Xie, Siwen Zhao, Sen Lin, Yujun Li

Frontiers in Bioengineering and Biotechnology · 07.05.2026 · 14

DOI: 10.3389/fbioe.2026.1819324 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Bioengineering and Biotechnology, online erschienen am 07.05.2026. Verfasst von Xianwei Zhang und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Engineering, Shandong University, Qingdao, China. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Remote photoplethysmography (rPPG) enables non-contact heart rate measurement from facial videos with growing health monitoring applications. Despite advances in deep learning methods, most existing approaches lack task-specific feature refinement across spatial and channel dimensions, which can dilute pulsatile information.

Methods

We propose two key contributions to address this challenge. First, a Multi-scale Difference Fusion Stem (MDFS) captures temporal dynamics through learnable fusion of multi-scale frame differences, providing noise-resilient representations. Second, a Spatial-Channel Optimized Pulse Enhancement (SCOPE) module performs adaptive spatial-channel refinement with gated fusion to amplify pulse-related features while suppressing interference.

Results

Comprehensive experiments on PURE, UBFC-rPPG, and MMPD datasets demonstrate state-of-the-art performance in both intra-dataset and cross-dataset evaluations.

Discussion

These results indicate that explicitly constructing multi-scale temporal cues and performing controlled spatial-channel refinement are effective for robust rPPG estimation under low-SNR conditions.

Schlagwörter

Stichwörter der Autor:innen

deep learningheart rate estimationmulti-scale frame difference fusionremote photoplethysmographyspatial and channel attention

Autor:innen und Institutionen

  • School of Information Science and Engineering, Shandong University, Qingdao, China.

Zitieren

APA

Zhang, X., Qiao, F., Zang, Q., Chen, Z., Xie, X., Zhao, S., Lin, S., & Li, Y. (2026). Noise-resilient spatial–channel refinement for robust remote photoplethysmography. Frontiers in Bioengineering and Biotechnology, 14. https://doi.org/10.3389/fbioe.2026.1819324

Vancouver

Zhang X, Qiao F, Zang Q, Chen Z, Xie X, Zhao S, et al. Noise-resilient spatial–channel refinement for robust remote photoplethysmography. Frontiers in Bioengineering and Biotechnology. 2026;14. doi:10.3389/fbioe.2026.1819324

BibTeX
@article{Zhang2026,
  author = {Zhang, Xianwei and Qiao, Feng and Zang, Qiaochu and Chen, Zhe and Xie, Xiaoting and Zhao, Siwen and Lin, Sen and Li, Yujun},
  title = {Noise-resilient spatial–channel refinement for robust remote photoplethysmography},
  journal = {Frontiers in Bioengineering and Biotechnology},
  year = {2026},
  volume = {14},
  doi = {10.3389/fbioe.2026.1819324}
}
Kostenlos starten →