# High-Fidelity rPPG Waveform Reconstruction from Palm Videos Using GANs

## TL;DR

This paper introduces a new method using GANs to reconstruct high-quality rPPG waveforms from palm videos, improving accuracy compared to existing techniques.

## Contribution

A novel GAN-based framework and a new dataset for high-fidelity rPPG waveform reconstruction from palm videos.

## Key findings

- The proposed method achieves an RMSE of 0.102 and a Pearson correlation of 0.987 in waveform reconstruction.
- The new dataset with palm-region videos and wrist PPG signals improves model training for accurate rPPG waveform recovery.
- The model outperforms existing methods in morphological accuracy of reconstructed rPPG waveforms.

## Abstract

Remote photoplethysmography (rPPG) enables non-contact acquisition of human physiological parameters using ordinary cameras, and has been widely applied in medical monitoring, human–computer interaction, and health management. However, most existing studies focus on estimating specific physiological metrics, such as heart rate and heart rate variability, while paying insufficient attention to reconstructing the underlying rPPG waveform. In addition, publicly available datasets typically record facial videos accompanied by fingertip PPG signals as reference labels. Since fingertip PPG waveforms differ substantially from the true photoplethysmography (PPG) signals obtained from the face, deep learning models trained on such datasets often struggle to recover high-quality rPPG waveforms. To address this issue, we collected a new dataset consisting of palm-region videos paired with wrist-based PPG signals as reference labels, and experimentally validated its effectiveness for training neural network models aimed at rPPG waveform reconstruction. Furthermore, we propose a generative adversarial network (GAN)-based pulse-wave synthesis framework that produces high-quality rPPG waveforms by denoising the mean green-channel signal. By incorporating time-domain peak-aware loss, frequency-domain loss, and adversarial loss, our method achieves promising performance, with an RMSE (Root Mean Square Error) of 0.102, an MAPE (Mean Absolute Percentage Error) of 0.028, a Pearson correlation of 0.987, and a cosine similarity of 0.989. These results demonstrate the capability of the proposed approach to reconstruct high-fidelity rPPG waveforms with improved morphological accuracy compared to noisy raw rPPG signals, rather than directly validating health monitoring performance. This study presents a high-quality rPPG waveform reconstruction approach from both data and model perspectives, providing a reliable foundation for subsequent physiological signal analysis, waveform-based studies, and potential health-related applications.