提出可插拔的时序归一化模块，提升远距离光电容积脉搏波信号精度。
A Plug-and-Play Temporal Normalization Module for Robust Remote Photoplethysmography
- 通过时序归一化捕捉长期特征，抑制运动与光照干扰。
- 在4个数据集上提升心率测量准确率34.3%至94.2%。
- 尤其适合小模型使用，机制清晰且兼容性强。
远程光电容积脉搏波（rPPG）从面部视频中细微的颜色变化提取脉搏信号，具有广阔健康应用前景。然而，现有rPPG方法多依赖连续帧间强度差异，忽略受运动或光照干扰的长期信号变化，导致精度下降。本文提出时序归一化（Temporal Normalization, TN）模块，可灵活嵌入任意端到端rPPG网络架构。通过去趋势后捕获长期时序归一化特征，有效缓解运动与光照伪影，显著提升预测性能。将TN集成至四种前沿rPPG方法，在四个常用数据集上的心率测量任务中，性能提升达34.3%至94.2%。值得注意的是，小模型中收益更为明显。本文还深入分析了TN有效性的内在机制。
原文摘要 · Abstract (English)
Remote photoplethysmography (rPPG) extracts PPG signals from subtle color changes in facial videos, showing strong potential for health applications. However, most rPPG methods rely on intensity differences between consecutive frames, missing long-term signal variations affected by motion or lighting artifacts, which reduces accuracy. This paper introduces Temporal Normalization (TN), a flexible plug-and-play module compatible with any end-to-end rPPG network architecture. By capturing long-term temporally normalized features following detrending, TN effectively mitigates motion and lighting artifacts, significantly boosting the rPPG prediction performance. When integrated into four state-of-the-art rPPG methods, TN delivered performance improvements ranging from 34.3% to 94.2% in heart rate measurement tasks across four widely-used datasets. Notably, TN showed even greater performance gains in smaller models. We further discuss and provide insights into the mechanisms behind TN's effectiveness.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。