FLOW: Feature-Level Optimal Warping for Generalized Remote Physiological Measurement

Bo Zhao; Junzhe Cao; Dan Guo; Dongmin Huang; Wenjin Wang; Tao Tan; Yue Sun; Zitong YU

cs.CVSep 30, 2026

FLOW: Feature-Level Optimal Warping for Generalized Remote Physiological Measurement

Authors: Bo Zhao, Junzhe Cao, Dan Guo, Dongmin Huang, Wenjin Wang, Tao Tan, Yue Sun, Zitong YU

Organizations: Great Bay University · Harbin Institute of Technology, Shenzhen · Hefei University of Technology · Southern University of Science and Technology · Macao Polytechnic University · Dongguan Key Laboratory for Intelligence and Information Technology

Abstract

Remote photoplethysmography (rPPG) enables non-contact physiological measurement but remains vulnerable to domain shifts from illumination, motion, and sensors. We propose \textbf{FLOW (Feature-Level Optimal Warping)}, an \emph{optimal transport--driven} framework for domain-generalized rPPG. FLOW integrates a \textbf{Temporal Refinement Module (TRM)} to stabilize temporal dynamics and a \textbf{Prototype-based Cross-Temporal Optimal Transport (PCOT)} module to achieve domain-invariant alignment via learnable prototypes.Beyond feature alignment, FLOW employs soft cross-temporal correspondence modeling that aligns temporal features in a flexible manner, allowing the model to respect and preserve the intrinsic rhythmic patterns of physiological signals. Moreover, the lightweight design of our modules allows seamless integration into existing end-to-end rPPG architectures without additional preprocessing. Two regularization terms further enforce source consistency and identity preservation. Theoretically, we derive a generalization bound under conditional optimal transport. Extensive experiments across four rPPG benchmarks show that FLOW achieves state-of-the-art cross-domain performance with lightweight design and strong physiological fidelity.

Figures & tables

Figure 1 : Overall architecture of FLOW. Given multi-domain video inputs, a shared backbone extracts intermediate features that are temporally refined by the TRM to suppress noise and unify dynamics. The refined sequences are then aligned through the PCOT module, which computes an optimal transport plan between temporal features and a learnable prototype bank. The framework is trained with the OT-based alignment loss $\mathcal{L}_{OT}$ , the source-consistency loss $\mathcal{L}_{sc}$ , the identity-preservation loss $\mathcal{L}_{id}$ and the task loss $\mathcal{L}_{task}$ . During training, the ground truth heart rate signals are used to guide and refine the transport plan for better prototype alignment. During inference, the model directly applies the learned transport plan to predict heart rates, without using any ground truth signals.

Model	Others $\rightarrow$ U			Others $\rightarrow$ P			Others $\rightarrow$ B			Others $\rightarrow$ M			Average
	MAE $\downarrow$	RMSE $\downarrow$	R $\uparrow$	MAE $\downarrow$	RMSE $\downarrow$	R $\uparrow$	MAE $\downarrow$	RMSE $\downarrow$	R $\uparrow$	MAE $\downarrow$	RMSE $\downarrow$	R $\uparrow$	MAE $\downarrow$	RMSE $\downarrow$	R $\uparrow$
Green [ 39 ]	19.73	31.00	0.37	10.09	23.85	0.34	6.89	10.39	0.60	21.68	27.69	-0.01	14.10	23.73	0.33
CHROM [ 9 ]	7.23	8.92	0.51	9.79	12.76	0.37	6.09	8.29	0.51	13.66	18.76	0.08	9.69	12.68	0.37
POS [ 42 ]	7.35	8.04	0.49	9.82	13.44	0.34	5.04	7.12	0.63	12.36	17.71	0.18	8.64	11.58	0.41
EfficientPhys [ 19 ]	12.87	18.80	0.19	7.15	15.04	0.23	32.30	34.00	-0.03	12.87	18.80	0.19	16.80	21.66	0.14
PhysFormer [ 52 ]	10.29	18.13	0.60	19.75	24.30	0.24	22.09	26.21	0.03	13.90	19.30	0.06	16.51	21.98	0.23

Table 1 : Multi-domain generalization evaluation. Best results are marked in bold . ‘+’ means domain generalization methods are based on ‘Baseline’.

Model	P+B			P+U			B+U			Average
	MAE $\downarrow$	RMSE $\downarrow$	R $\uparrow$	MAE $\downarrow$	RMSE $\downarrow$	R $\uparrow$	MAE $\downarrow$	RMSE $\downarrow$	R $\uparrow$	MAE $\downarrow$	RMSE $\downarrow$	R $\uparrow$
PhysNet [ 49 ]	13.20	16.70	0.23	11.00	17.30	0.28	13.50	17.00	0.09	12.57	17.00	0.20
PhysFormer [ 52 ]	13.90	18.60	0.21	11.40	17.50	0.23	13.20	16.50	0.12	12.83	17.53	0.19
EfficientPhys [ 19 ]	11.90	18.50	0.21	11.80	18.90	0.22	15.50	20.80	0.03	13.07	19.40	0.15
RhythmFormer [ 59 ]	13.98	19.46	0.12	10.50	16.72	0.28	11.70	16.56	0.18	12.06	17.58	0.19
NEST [ 20 ]	10.85	15.45	0.33	9.90	14.82	0.36	10.64	15.12	0.31	10.46	15.13	0.33

Table 2 : Limited-source domain generalization performance on MMPD. Best results are in bold .

Model	P+M			M+U			P+U			Average
	MAE $\downarrow$	RMSE $\downarrow$	R $\uparrow$	MAE $\downarrow$	RMSE $\downarrow$	R $\uparrow$	MAE $\downarrow$	RMSE $\downarrow$	R $\uparrow$	MAE $\downarrow$	RMSE $\downarrow$	R $\uparrow$
PhysNet [ 49 ]	20.97	24.75	0.01	11.40	16.72	0.14	15.34	21.48	-0.29	15.90	20.98	-0.05
PhysFormer [ 52 ]	14.86	18.26	0.03	10.87	16.20	0.08	18.23	22.17	0.07	14.65	18.88	0.06
EfficientPhys [ 19 ]	4.15	7.14	0.77	3.00	5.18	0.89	3.00	5.18	0.89	3.38	5.83	0.85
RhythmFormer [ 59 ]	3.55	5.35	0.90	6.20	11.23	0.49	3.90	6.51	0.82	4.55	7.70	0.74
NEST [ 20 ]	3.32	5.04	0.92	3.71	5.67	0.87	3.15	4.88	0.93	3.39	5.20	0.91

Table 3 : Limited-source domain generalization performance on BUAA-MIHR. Best results are in bold .

Table 4 : Comparison of different domain-alignment modules applied to the PhysFormer backbone (values are MAE

\downarrow

/RMSE

\downarrow

). “MMD” and “CORAL” are standard alignment baselines, and “FLOW” is our proposed method.

	BUAA		MMPD
	MAE $\downarrow$	RMSE $\downarrow$	MAE $\downarrow$	RMSE $\downarrow$
FLOW	2.23	3.36	7.38	13.12
FLOW(w/o TRM)	3.12	4.61	8.16	14.10
FLOW(w/o PCOT)	4.67	6.13	10.24	14.94

Table 5 : Ablation results on model components. ”FLOW” denotes the full FLOW model with both TRM and PCOT enabled.

$L_{\text{OT}}$	$L_{\text{id}}$	$L_{\text{sc}}$	BUAA		MMPD
			MAE $\downarrow$	RMSE $\downarrow$	MAE $\downarrow$	RMSE $\downarrow$
$\checkmark$			4.63	6.32	9.73	14.32
	$\checkmark$		4.57	5.89	9.82	13.96
$\checkmark$	$\checkmark$		2.44	4.12	8.23	14.42
$\checkmark$		$\checkmark$	3.63	5.61	7.98	13.17
	$\checkmark$	$\checkmark$	3.77	5.72	8.87	14.71

Table 6 : Ablation study on loss functions.

Figure 2 : Visualization of FLOW’s effectiveness across different backbones and cross-domain settings.

Panel of Figure 3 — Figure 3 : Ablations on the structure of PCOT and TRM modules.

Explore similar work

StreamPPG: Low-Latency rPPG Estimation via Consistent Privileged Learning
Jun 22, 2026Yiming Li, Yihan Yang, Yuguang Chu +4Remote Photoplethysmography Physiological Signals
ARXIV
PhysFlow: Frequency Decoupled with Dual-Field Rectified Flow for Remote Photoplethysmography
Jun 22, 2026Zixu Li, jianjun Qian, Hang Shao +2Remote Photoplethysmography Rectified Flow
PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China · College of Computer Science and Technology, Qingdao University, Qingdao 266071, China
FCUS-rPPG: A Fast-Converging Unsupervised Framework for Remote Photoplethysmography via Gradient Oscillation Suppression
Jun 2, 2026Jiajie Li, Yu Liu, Rencheng Song +2Remote Photoplethysmography Unsupervised
Department of Biomedical Engineering, and also with Anhui Province Key Laboratory of Measuring Theory and Precision Instrument, Hefei University of Technology, Hefei 230009, China · Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei 230026, China

Jun 22, 2026, cs.CVJ/K move · Enter open · S save

StreamPPG: Low-Latency rPPG Estimation via Consistent Privileged Learning

Yiming Li, Yihan Yang, Yuguang Chu, Yuanhui Hu+3

ARXIV

Remote Photoplethysmography Physiological Signals Streaming Inference Temporal Convolutional Networks

Open paper AskPDF arXiv

Remote photoplethysmography (rPPG) estimates the blood volume pulse (BVP) signal from facial videos, enabling contact-free health monitoring. Conventional clip-wise approaches, which use video clips as input, require capturing over one hundred frames before inference, thus introducing several seconds of delay and hindering real-time use. Meanwhile, frame-wise approaches struggle to capture long-range temporal and periodic features of physiological rhythms, and therefore lead to reduced estimation accuracy. To overcome these issues, we propose StreamPPG, a unified architecture that enables low-latency frame-wise physiological signal estimation while achieving competitive accuracy compared with clip-wise approaches. StreamPPG is trained under a consistent privileged learning (CPL) strategy, which leverages ground-truth rPPG signals as privileged information to enhance the model's representation capability. Extensive experiments demonstrate that StreamPPG achieves state-of-the-art accuracy across multiple datasets while maintaining real-time throughput on edge devices.

Abstract

Explore similar work

StreamPPG: Low-Latency rPPG Estimation via Consistent Privileged Learning

PhysFlow: Frequency Decoupled with Dual-Field Rectified Flow for Remote Photoplethysmography

FCUS-rPPG: A Fast-Converging Unsupervised Framework for Remote Photoplethysmography via Gradient Oscillation Suppression