AR app with rear camera face anchor
Trying to develop an app with face tracking using the rear camera of an iPad
or iPhone. All documentation available seems to refer only to front camera cases. Am I trying the impossible here?
The Apple Support Community will permanently close on November 20, 2026. Starting today, the site will no longer accept new posts and is available in a read-only state.
You can continue to find trusted guidance and support on the official Apple Support site.
We want to thank the community members who have contributed their time and expertise to help others with their Apple products.
The Apple Support Community will permanently close on November 20, 2026. Starting today, the site will no longer accept new posts and is available in a read-only state.
You can continue to find trusted guidance and support on the official Apple Support site.
We want to thank the community members who have contributed their time and expertise to help others with their Apple products.
Trying to develop an app with face tracking using the rear camera of an iPad
or iPhone. All documentation available seems to refer only to front camera cases. Am I trying the impossible here?
While a dual camera back can capture depth, the rear cameras are not TrueDepth so no Face ID nor related support.
Face detection runs a parallel scan using an IR point scan. It’s this point scan that is underneath Face ID.
Well, you could implement face detection support yourself, but that’s a larger (and riskier) ML project than you probably intended to start.
Improve Object Detection models in Create ML - Tech Talks - Videos - Apple Developer
I don’t think AR kit object detection will get you there, either:
And the LIDAR scanner uses a very different hardware design and scan design:
https://www.eyerys.com/articles/how-apples-lidar-sensor-differs-one-its-truedepth-face-id
While a dual camera back can capture depth, the rear cameras are not TrueDepth so no Face ID nor related support.
Face detection runs a parallel scan using an IR point scan. It’s this point scan that is underneath Face ID.
Well, you could implement face detection support yourself, but that’s a larger (and riskier) ML project than you probably intended to start.
Improve Object Detection models in Create ML - Tech Talks - Videos - Apple Developer
I don’t think AR kit object detection will get you there, either:
And the LIDAR scanner uses a very different hardware design and scan design:
https://www.eyerys.com/articles/how-apples-lidar-sensor-differs-one-its-truedepth-face-id
Thank you for the extremely detailed information. I wasn’t fully aware that the LiDAR Scanner and the front face scanner were different hardware design.
It just somehow seemed doable but I guess it’ll have to wait for the AR revolution that the Apple AR device is suppose to bring.
AR app with rear camera face anchor