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

arXiv:2609.38913v1 Announce Type: new Abstract: Remote photoplethysmography (rPPG) enables non-contact physiological measurement but remains vulnerable to domain shifts from illumination, motion, and sensors. We propose extbf{FLOW (Feature-Level Optimal Warping)}, an optimal transport--driven framework for domain-generalized rPPG. FLOW integrates a extbf{Temporal Refinement Module (TRM)} to stabilize temporal dynamics and a extbf{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.

Related

• RPM-Distill: Physiology-guided Adaptive Cross-modal Distillation for Robust Remote Physiological Measurement
• VideoPulse: Neonatal heart rate and peripheral capillary oxygen saturation (SpO2) estimation from contact free video
• Rhythm-Structured Predictive Learning for Remote Photoplethysmography
• PhysVR: Vision-Language Model Guided Interference-aware Temporal Feature Refinement for Remote Physiological Measurement

Source: arXiv cs.CV | 2026-10-01