Activity counts measure attention, not model quality. Missing counts are unknown. Publication status follows the linked source; a listed venue alone does not confirm peer review.
Vision4PPG turns 1D PPG into 2D images (STFT magnitude, STFT phase, and recurrence plots) and fine-tunes public vision foundation models, DINOv3 and SigLIP-2 ViT-B (86M parameters), with LoRA. It is an adaptation of vision models, not a PPG-pretrained foundation model. In the authors' Table 1, those vision models win 9 of 14 diastolic/systolic MAE comparisons against fully tuned MOMENT-385M and PPG-GPT-345M; SigLIP-2's Aurora-Oscillometric DBP/SBP MAE is 5.32/18.57 mmHg. The bed BCG set is an exception, where MOMENT and PPG-GPT report lower error than either vision model.
- Authors
- Kataria, Ermis, Panchumarthi, Wang, Hu (Emory Nursing)
- Signals
- PPG
arXiv:2510.10366v1 (11 Oct 2025); DOI 10.48550/arXiv.2510.10366
DINOv3 and SigLIP-2 ViT-B, 86M; LoRA on Q, K, V (r=8, alpha=16, dropout 0.05)
- Table 1
SigLIP-2 Aurora-Oscillometric DBP/SBP MAE 5.32/18.57 mmHg
- Authors
vision FMs win 9/14 DBP/SBP comparisons vs MOMENT-385M and PPG-GPT-345M
- Table 2
PPG-GPT HR MAE 7.83 bpm (DaLiA) beats both vision models; DINOv3 respiration MAE 4.41 breaths/min (BIDMC) and SpO2 MAE 2.19% (MIMIC-III)
- Code
github.com/saurabh-kataria/Vision4PPG; no weights released with the preprint
- Type
- FM adaptation
- Modalities
- PPG
- Form factor
- Imagified PPG vision fm
- Parameters
- 86M
- Architecture
- DINOv3 and SigLIP-2 ViT-B (86M) with LoRA on Q, K, and V (r=8, alpha=16, dropout 0.05); 1D PPG rendered as STFT magnitude, STFT phase, or recurrence plots
- Venue
- arXiv preprint
- Year
- 2025
- Weights
- Not released
- Licence
- Not reported
- Caveats
- Not reported
- Datasets
- Added
- Oct 26, 2026
- Updated
- Oct 26, 2026
Abstract
Photoplethysmography (PPG) sensor in wearable and clinical devices provides valuable physiological insights in a non-invasive and real-time fashion. Specialized Foundation Models (FM) or repurposed time-series FMs are used to benchmark physiological tasks. Our experiments with fine-tuning FMs reveal that Vision FM (VFM) can also be utilized for this purpose and, in fact, surprisingly leads to state-of-the-art (SOTA) performance on many tasks, notably blood pressure estimation. We leverage VFMs by simply transforming one-dimensional PPG signals into image-like two-dimensional representations, such as the Short-Time Fourier transform (STFT). Using the latest VFMs, such as DINOv3 and SIGLIP-2, we achieve promising performance on other vital signs and blood lab measurement tasks as well. Our proposal, Vision4PPG, unlocks a new class of FMs to achieve SOTA performance with notable generalization to other 2D input representations, including STFT phase and recurrence plots. Our work improves upon prior investigations of vision models for PPG by conducting a comprehensive study, comparing them to state-of-the-art time-series FMs, and demonstrating the general PPG processing ability by reporting results on six additional tasks. Thus, we provide clinician-scientists with a new set of powerful tools that is also computationally efficient, thanks to Parameter-Efficient Fine-Tuning (PEFT) techniques.
Verbatim fromarXiv· arXiv metadata (abstracts are released under CC0)
Key results
How it works
Datasets linked in the hub; pretraining vs evaluation roles follow the paper.
- Pretraining data
- Public vision corpora (DINOv3 LVD-1689M; SigLIP-2 WebLI), not PPG
- Architecture
- DINOv3 and SigLIP-2 ViT-B (86M) with LoRA on Q, K, and V (r=8, alpha=16, dropout 0.05); 1D PPG rendered as STFT magnitude, STFT phase, or recurrence plots
- Inputs
- PPG
- Approach
- PPG · foundation model · vision · emory · cuffless bp · lora
Datasets· 6
PPG-BP Database (Guilin / Liang 2018)219 subjects · PPG
Brno University of Technology Smartphone PPG Database (BUT PPG)50 subjects · PPG · ECG
VitalVideosface video + contact PPG + BP/SpO2 (Europe-1, Africa-1, Worldwide)850 subjects · PPG
PPG-DaLiAPPG dataset for motion compensation / HR15 subjects · PPG · ECG · IMU
BIDMC PPG and Respiration (Pimentel 2016 / PhysioNet)53 subjects · PPG · ECG · SpO₂
Bed-Based BCG (Carlson, K-State)40 adults, bed BCG + ECG + PPG + Finometer PRO continuous BP (IEEE DataPort OA)40 subjects · PPG · ECG · BP
Papers· 1
Cite
APA
Kataria, S., Ermis, A., Panchumarthi, L. Y., Wang, M., & Hu, X. (2025). Vision4PPG: Emergent PPG Analysis Capability of Vision Foundation Models for Vital Signs like Blood Pressure. arXiv preprint. https://doi.org/10.48550/arXiv.2510.10366
BibTeX
@misc{kataria2025vision4ppg,
title = {{Vision4PPG: Emergent PPG Analysis Capability of Vision Foundation Models for Vital Signs like Blood Pressure}},
author = {Kataria, Saurabh and Ermis, Ayca and Panchumarthi, Lovely Yeswanth and Wang, Minxiao and Hu, Xiao},
year = {2025},
howpublished = {arXiv preprint},
doi = {10.48550/arXiv.2510.10366},
eprint = {2510.10366},
archivePrefix = {arXiv}
}Built from the hub record. Check it against the publisher before submitting.
History
Added to the ChatPPG research hub
Connections
Open in the graph explorerPapers
- Vision4PPG: Emergent PPG Analysis Capability of Vision Foundation Models for Vital Signs like Blood PressurePaper on this modelarXiv preprint · 2025
Bridging ECG and PPG: Latent-Space Prediction for Robust Physiological AnalysisAlso uses Brno University of Technology Smartphone PPG Database (BUT PPG)KDD '26 · 2026
PPG-Bench: A Unified Benchmark for PPG Foundation ModelsAlso uses PPG-BP Database (Guilin / Liang 2018)arXiv preprint · 2026
