Template Collapse and Information-Theoretic Limits in Camera rPPG Pulse Morphology Restoration
2026-06-02 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors studied whether regular phone cameras can capture unique heart pulse shapes that reveal artery stiffness from a single heartbeat cycle. They tested many machine learning methods on data from different people but found none could reliably identify individual heart pulse shapes beyond a general pattern. Their results show that current camera-based methods can't distinguish detailed personal artery information from just one heartbeat. They suggest that assessing cross-subject correlation is important to avoid misleading conclusions in this kind of research.
remote photoplethysmographyarterial stiffnesswaveform morphologymachine learning architecturescross-subject correlationSupervised Contrastive learningvariational autoencoderheartbeat cycleconsumer camerassignal reconstruction
Authors
Achraf Ben Ahmed
Abstract
Objective: Consumer face camera remote photoplethysmography (rPPG) enables passive cardiovascular monitoring, but whether single-cycle waveform morphology encoding arterial stiffness biomarkers is recoverable from this measurement has not been characterised. Methods: We evaluated 16 architectures spanning six families on 153 subjects across three datasets, introducing cross-subject Pearson r to distinguish subject-specific recovery from template collapse. Results: No architecture recovered subject-specific morphology (cross-subject r range 0.773--0.9999; ground-truth ceiling 0.601). Supervised Contrastive (SupCon) converged to log N = 4.844, constituting the strongest available empirical evidence that no discriminative morphological structure is extractable from single-cycle rPPG by the encoder families tested. The VAE decoder restores population-level harmonic content absent from the rPPG input (H2/H1: 0.310 output vs. 0.275 input), generalising zero-shot to UBFC (r = +0.708); a directional hallucination gap (p = 0.150) suggests partial signal reading. Anti-collapse objectives fail when input carries no discriminative structure. Significance: Consumer cameras cannot encode individual arterial morphology; cross-subject r is a necessary collapse diagnostic for waveform reconstruction benchmarks.