RECORD
Remote Photoplethysmography in Real-World and Extreme Lighting Scenarios
Computer Vision and Pattern Recognition · Submitted 14 Mar 2025
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Extensive experiments show the competitiveness and performance of our model in rPPG prediction across datasets and scenes.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Physiological activities can be manifested by the sensitive changes in facial imaging. While they are barely observable to our eyes, computer vision manners can, and the derived remote photoplethysmography (rPPG) has shown considerable promise. However, existing studies mainly rely on spatial skin recognition and temporal rhythmic interactions, so they focus on identifying explicit features under ideal light conditions, but perform poorly in-the-wild with intricate obstacles and extreme illumination exposure. In this paper, we propose an end-to-end video transformer model for rPPG. It strives to eliminate complex and unknown external time-varying interferences, whether they are sufficient to occupy subtle biosignal amplitudes or exist as periodic perturbations that hinder network training. In the specific implementation, we utilize global interference sharing, subject background reference, and self-supervised disentanglement to eliminate interference, and further guide learning based on spatiotemporal filtering, reconstruction guidance, and frequency domain and biological prior constraints to achieve effective rPPG. To the best of our knowledge, this is the first robust rPPG model for real outdoor scenarios based on natural face videos, and is lightweight to deploy. Extensive experiments show the competitiveness and performance of our model in rPPG prediction across datasets and scenes.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Physiological activities can be manifested by the sensitive changes in facial imaging. | background 1.00 | 0.05 | 0.02 | asserted 0.97 |
| s1 | While they are barely observable to our eyes, computer vision manners can, and the derived remote photoplethysmography (rPPG) has shown considerable promise. | background 1.00 | 0.11 | 0.04 | asserted 0.98 |
| s2 | However, existing studies mainly rely on spatial skin recognition and temporal rhythmic interactions, so they focus on identifying explicit features under ideal light conditions, but perform poorly in-the-wild with intricate obstacles and extreme illumination exposure. | gap 0.90 | 0.08 | 0.04 | asserted 1.00 |
| s3 | In this paper, we propose an end-to-end video transformer model for rPPG. | contribution 0.77 | 0.87 | 0.05 | asserted 0.99 |
| s4 | It strives to eliminate complex and unknown external time-varying interferences, whether they are sufficient to occupy subtle biosignal amplitudes or exist as periodic perturbations that hinder network training. | contribution 0.51 | 0.43 | 0.06 | asserted 0.74 |
| s5 | In the specific implementation, we utilize global interference sharing, subject background reference, and self-supervised disentanglement to eliminate interference, and further guide learning based on spatiotemporal filtering, reconstruction guidance, and frequency domain and biological prior constraints to achieve effective rPPG. | method 1.00 | 0.93 | 0.08 | asserted 1.00 |
| s6 | To the best of our knowledge, this is the first robust rPPG model for real outdoor scenarios based on natural face videos, and is lightweight to deploy. | contribution 0.99 | 0.85 | 0.25 | asserted 0.99 |
| s7 | Extensive experiments show the competitiveness and performance of our model in rPPG prediction across datasets and scenes. | result 0.99 | 0.95 | 0.56 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Physiological activities can be manifested by the sensitive changes in facial imaging. While they are barely observable to our eyes, computer vision manners can, and the derived remote photoplethysmography (rPPG) has shown considerable promise. However, existing studies mainly rely on spatial skin recognition and temporal rhythmic interactions, so they focus on identifying explicit features under ideal light conditions, but perform poorly in-the-wild with intricate obstacles and extreme illumination exposure. In this paper, we propose an end-to-end video transformer model for rPPG. It strives to eliminate complex and unknown external time-varying interferences, whether they are sufficient to occupy subtle biosignal amplitudes or exist as periodic perturbations that hinder network training. In the specific implementation, we utilize global interference sharing, subject background reference, and self-supervised disentanglement to eliminate interference, and further guide learning based on spatiotemporal filtering, reconstruction guidance, and frequency domain and biological prior constraints to achieve effective rPPG. To the best of our knowledge, this is the first robust rPPG model for real outdoor scenarios based on natural face videos, and is lightweight to deploy. Extensive experiments show the competitiveness and performance of our model in rPPG prediction across datasets and scenes.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites
Compares with 1 paper
-
Furthermore, in Fig. [ref], the scene comparison we conducted for methods [ref] is based on weights trained on MR-NIRP.
RhythmFormer: Extracting Patterned rPPG Signals based on Periodic Sparse Attention · Comparison with the state-of-the-art methods · 0.98
Cites as background 2 papers
-
Recently, researchers have developed many learning-based visual rPPG networks, which have continuously improved task-oriented performances in facial ROI attention [ref] , spatiotemporal enhancement [ref] , and long-term time perception [ref] .
RhythmFormer: Extracting Patterned rPPG Signals based on Periodic Sparse Attention · Learning-based rPPG in daily life · 0.90
-
Moreover, researchers have proposed approaches such as frequency reconstruction [ref] , conductive inference [ref] , multi-modality fusion [ref] , and pseudo-label recombination [ref] .
Fully Test-Time rPPG Estimation via Synthetic Signal-Guided Feature Learning · Self-supervised learning for rPPG · 0.90
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.