# A Plug-and-Play Temporal Normalization Module for Robust Remote Photoplethysmography

arXiv: https://arxiv.org/abs/2411.15283 · HTML: https://mlsanity.com/paper/2411.15283/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Nov 2024.

## Built on by (most cited first, 6 of 6)

- [Memory-efficient Low-latency Remote Photoplethysmography through Temporal-Spatial State Space Duality](https://mlsanity.com/paper/2504.01774/) (2025)
- [M3PD Dataset: Dual-view Photoplethysmography (PPG) Using Front-and-rear Cameras of Smartphones in Lab and Clinical Settings](https://mlsanity.com/paper/2511.02349/) (2025)
- [Exploring Remote Physiological Signal Measurement under Dynamic Lighting Conditions at Night: Dataset, Experiment, and Analysis](https://mlsanity.com/paper/2507.04306/) (2025)
- [FacePhys: State of the Heart Learning](https://mlsanity.com/paper/2512.06275/) (2025)
- [Illumination-Robust Camera-Based Heart-Rate Estimation for Physiological Sensing in Robots](https://mlsanity.com/paper/2606.12378/) (2026)
- [Cross-Dataset Transfer and Reliability of Explainable Artificial Intelligence for RhythmFormer Remote Photoplethysmography](https://mlsanity.com/paper/2609.03663/) (2026)

## Abstract (arXiv)

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.