PhysiologicAILab/FactorizePhys

FactorizePhys: Matrix Factorization for Multidimensional Attention in Remote Physiological Sensing [NeurIPS 2024]

42
/ 100
Emerging

This project helps researchers and engineers accurately measure blood volume pulse (BVP) signals from standard video recordings. It takes video frames as input and produces estimated BVP signals, enabling non-contact physiological monitoring. This is for professionals working in healthcare technology, remote sensing, or human-computer interaction who need precise physiological data without physical sensors.

No commits in the last 6 months.

Use this if you need to extract highly accurate blood volume pulse signals from video recordings, especially when dealing with complex spatial-temporal data.

Not ideal if your primary goal is real-time, ultra-low latency monitoring on embedded systems with limited computational resources.

remote-health-monitoring physiological-measurement computer-vision non-contact-sensing biometric-analysis
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

30

Forks

9

Language

Python

License

Last pushed

Aug 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/PhysiologicAILab/FactorizePhys"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.