It's interesting how you've dug into facial regions for rPPG; what if individual skin types or lighting also impacts the data quality for certain areas?
Thank you for your message! Here is a reply from Maksym: Skin type and lighting do play a tangible role in rPPG signal quality, and your point is right on target. It was such a critical aspect that I dedicated a separate study to it, focusing on how skin tone and demographic diversity affect heart-rate estimation. The results are available here: https://www.nature.com/articles/s41746-025-01973-9 In practice, rPPG relies not on the absolute color of a facial region but on the changes in that color over time. Under stable lighting, this makes the method more resilient: We track subtle variations caused by blood flow rather than the baseline skin tone. To reduce noise from illumination or motion, we also apply signal-processing steps such as band-pass filtering and other correction techniques. Still, darker skin tones and demographic factors introduce additional complexity -> hence the dedicated paper to highlight these challenges. If you’d like to continue the conversation or explore the research further, feel free to connect with me on LinkedIn: https://www.linkedin.com/in/maksym-bondarenko-ua/
It's interesting how you've dug into facial regions for rPPG; what if individual skin types or lighting also impacts the data quality for certain areas?
Thank you for your message! Here is a reply from Maksym: Skin type and lighting do play a tangible role in rPPG signal quality, and your point is right on target. It was such a critical aspect that I dedicated a separate study to it, focusing on how skin tone and demographic diversity affect heart-rate estimation. The results are available here: https://www.nature.com/articles/s41746-025-01973-9 In practice, rPPG relies not on the absolute color of a facial region but on the changes in that color over time. Under stable lighting, this makes the method more resilient: We track subtle variations caused by blood flow rather than the baseline skin tone. To reduce noise from illumination or motion, we also apply signal-processing steps such as band-pass filtering and other correction techniques. Still, darker skin tones and demographic factors introduce additional complexity -> hence the dedicated paper to highlight these challenges. If you’d like to continue the conversation or explore the research further, feel free to connect with me on LinkedIn: https://www.linkedin.com/in/maksym-bondarenko-ua/