Template Collapse and Information-Theoretic Limits in Camera rPPG Pulse Morphology Restoration
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 41 references that are in the map. First posted on arXiv 2 Jun 2026.
Builds on
23 of 41 references.
References · 23
- 2020Supervised Contrastive Learningcited by 2,829
- 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,057
- 2021Understanding Dimensional Collapse in Contrastive Self-supervised Learningcited by 378
- 2017Toward Multimodal Image-to-Image Translationcited by 296
- 2015Cross Modal Distillation for Supervision Transfercited by 175
- 2020Joint Generative and Contrastive Learning for Unsupervised Person Re-identificationcited by 58
- 2020Joint Contrastive Learning with Infinite Possibilitiescited by 31
- 2022Motion-Focused Contrastive Learning of Video Representationscited by 23
- 2019Deep Latent Space Learning for Cross-modal Mapping of Audio and Visual Signalscited by 20
- 2021Towards Fine-grained Visual Representations by Combining Contrastive Learning with Image Reconstruction and Attention-weighted Poolingcited by 13
- 2021Guided Variational Autoencoder for Speech Enhancement With a Supervised Classifiercited by 12
- 2024How Suboptimal is Training rPPG Models with Videos and Targets from Different Body Sites?cited by 9
11 more
- 2024Self-supervised contrastive learning performs non-linear system identificationcited by 9
- 2026SIGMA-PPG: Statistical-prior Informed Generative Masking Architecture for PPG Foundation Modelcited by 8
- 2025PPGFlowECG: Latent Rectified Flow with Cross-Modal Encoding for PPG-Guided ECG Generation and Cardiovascular Disease Detectioncited by 7
- 2019Cross-modal Variational Auto-encoder with Distributed Latent Spaces and Associatorscited by 5
- 2025Variational Supervised Contrastive Learningcited by 5
- 2026FreqPhys: Repurposing Implicit Physiological Frequency Prior for Robust Remote Photoplethysmographycited by 5
- 2025Reduction of motion artifacts from photoplethysmography signals using learned convolutional sparse codingcited by 2
- 2018SyncGAN: Synchronize the Latent Space of Cross-modal Generative Adversarial Networkscited by 1
- 2025Weighted Combination and Singular Spectrum Analysis Based Remote Photoplethysmography Pulse Extraction in Low-light Environmentscited by 1
- 2025SkinMap: Weighted Full-Body Skin Segmentation for Robust Remote Photoplethysmographycited by 1
- 2026ToTMNet: FFT-Accelerated Toeplitz Temporal Mixing Network for Lightweight Remote Photoplethysmographycited by 1
Built on by
Not cited yet.