Inpainting for artifact restoration in rPPG signals: a tool for real-world applicability in wellness and driver monitoring systems
Open Access
- 16 April 2026
- journal article
- Published by IOP Publishing in Physiological Measurement
- Vol. 47 (5)
Abstract
Objective. Photoplethysmography (PPG) and remote photoplethysmography (rPPG) are widely used non-invasive techniques for monitoring cardiovascular parameters. However, signal artifacts from motion, lighting variations, and environmental noise pose significant challenges for accurate physiological measurement, particularly in non-contact rPPG systems. To address these issues, we propose a novel generative inpainting framework designed to restore corrupted segments of PPG and rPPG signals. Approach. Our method leverages a large-scale synthetic dataset that spans a broad range of heart rates (30–180 beats per minute) and incorporates diverse artifact profiles to simulate real-world conditions. The inpainting model is built upon a custom Wasserstein GAN architecture, using a gradient penalty to ensure stable adversarial training. This selective reconstruction approach targets only the corrupted segments while preserving the integrity of high-quality signal portions. Main results. Results show that the proposed framework improves signal quality compared to corrupted signals. For synthetic datasets spanning heart rates from 30 to 180 beats per minute, signal-to-noise ratio increases from approximately −0.65–−0.20 dB to 3.27–4.16 dB after inpainting, while the mean absolute error decreases from 0.08–0.09 to 0.05–0.06. Feature-level similarity also improves, with Fréchet Encoder Distance reduced from 0.12 to 0.03 for real PPG and from 0.07 to 0.01 for real rPPG, and consistent reductions observed across all synthetic heart-rate ranges (from 0.23–0.47 to 0.01–0.04). Heart-rate estimates derived from the reconstructed signals are statistically equivalent to those obtained from clean references. Significance. The proposed generative inpainting framework effectively restores degraded PPG and rPPG signals and preserves heart-rate estimates, supporting its use in non-critical physiological monitoring applications such as wellness monitoring and automotive contexts. Validation on real data was limited to relatively clean, resting-state recordings; further studies are required to assess performance under high-motion and real-world conditions.Keywords
This publication has 37 references indexed in Scilit:
- A State‐Of‐The‐Art Survey of Remote Photoplethysmography for Contactless Health Parameters SensingWIREs Data Mining and Knowledge Discovery, 2025
- Optimal signal quality index for remote photoplethysmogram sensingnpj Biosensing, 2024
- Synthetic Data for Video Surveillance Applications of Computer Vision: A ReviewInternational Journal of Computer Vision, 2024
- Robust in-vehicle heartbeat detection using multimodal signal fusionScientific Reports, 2023
- Remote photoplethysmography for heart rate measurement: A reviewBiomedical Signal Processing and Control, 2023
- Review on remote heart rate measurements using photoplethysmographyMultimedia Tools and Applications, 2023
- Fréchet AutoEncoder Distance: A new approach for evaluation of Generative Adversarial NetworksComputer Vision and Image Understanding, 2023
- Two-Stage Motion Artifact Reduction Algorithm for rPPG Signals Obtained from Facial Video RecordingsArabian Journal for Science and Engineering, 2023
- Heart rate variability: are you using it properly? Standardisation checklist of proceduresBrazilian Journal of Physical Therapy, 2020
- The importance of interpretability and visualization in machine learning for applications in medicine and health careNeural Computing and Applications, 2019