CTA-Net: A Lightweight Network for Remote Photoplethysmography Signal Estimation With Channel–Temporal Attention

In recent years, remote photoplethysmography (rPPG) technology has made significant strides in non-contact health monitoring. However, existing methods are often constrained by high computational costs and large model parameter sizes, making them unsuitable for resource-constrained environments. To address these challenges, we propose CTA-Net, a lightweight rPPG estimation network that integrates a Channel-Temporal Attention Module (CTAM) to efficiently capture spatiotemporal features associated with rPPG signals. By constructing a multi-scale spatiotemporal map (MSTMap) through the fusion of RGB and YUV color spaces, CTA-Net enhances feature extraction capabilities while maintaining low computational complexity. The proposed method demonstrates outstanding performance on the PURE, COFACE, and UBFC datasets, achieving state-of-the-art (SOTA) results on the PURE and COFACE datasets, and near-SOTA performance on the UBFC dataset. Compared to representative deep learning models in the field, our method significantly reduces the model parameters and computational workload, showcasing a significant lightweight advantage. Furthermore, ablation studies validate the effectiveness of the MSTMap fusion strategy, CTAM configuration, activation function choice, and Cosine Annealing Learning Rate (CALR) adjustment in improving model performance. Overall, the proposed method strikes an optimal balance between estimation accuracy and computational efficiency. Our codes will be available at https://github.com/Jry-M/CTA-Net.git.