The field of physiological signal estimation and biometric authentication is rapidly evolving, with a focus on developing innovative methods for accurate and robust signal processing. Recent developments have centered around improving the estimation of heart rate, heart rate variability, and other vital signs from various signals, including face videos, radar signals, and photoplethysmography (PPG) signals. Notably, deep learning models have been proposed to enhance the accuracy of these estimations, with some models demonstrating significant improvements over traditional methods. Additionally, there is a growing interest in biometric authentication using PPG signals, with researchers exploring ways to improve the robustness of these systems to motion artifacts, illumination changes, and inter-subject variability. Overall, the field is moving towards the development of more accurate, robust, and practical systems for physiological signal estimation and biometric authentication.

Some noteworthy papers in this area include: VitalLens 2.0, which introduces a new deep learning model for estimating physiological signals from face video, achieving state-of-the-art results. LifWavNet, which proposes a lifting wavelet network for non-contact ECG reconstruction from radar signals, outperforming existing methods. M3PD Dataset, which introduces a publicly available dual-view mobile photoplethysmography dataset and proposes a model that fuses facial and fingertip views to improve heart rate estimation. A Hybrid Deep Learning Model for Robust Biometric Authentication, which proposes a lightweight and cost-effective biometric authentication framework based on PPG signals extracted from low-frame-rate fingertip videos, achieving an authentication accuracy of 98%.