Is it possible to get the 3 dimensional location of points on a face mask?
For example, let's say I make a face mask with tracking dots on them. The idea would be to apply the face mask to the person, find the dots using a script, and then get their position in 3 dimensional space to then track and deform a 3d mesh. Essentially facial capture using the face mask to provide the tracking points.
What system are you using?
Have you downloaded the latest version of Lens Studio?
Is this issue causing Lens Studio to crash?
Version
Graphics
Attach a screenshot of the issue:
Name:
Email:
What is this most relevant to?
Please enter a brief description of your issue:
Unfortunately, it's likely due to the operating system or hardware you're using – since they don't meet the system requirements for Lens Studio.
Still, we hear you loud and clear, and are logging the issue in case there's ever a workaround we can provide!
Minimum Requirements
Operating System: Windows 10 (64 bit); MacOS 10.11+
Hardware: Minimum of Intel Core i3 2.5Ghz or AMD Phenom II 2.6Ghz with 4 GB RAM; Intel HD Graphics 4000 / Nvidia GeForce 710 / AMD Radeon HD 6450 or better; screen resolution of 1280x768 or higher
Keep an eye out for a followup email from us. We may have a couple more questions for you, or we might already have a solution to offer.
Happy creating!
Hi Michael,
At this time Lens Studio does not provide the ability to track 3D position on a face mask. We'll pass it on to the engineers that there is some interest.
If you can describe a bit more about what you're trying to achieve, we might be able to help you think of something.
For example, take a look at the Paperhead Template to see how we can track different parts of the face to get an understanding of what the user is doing with their face. This post also has good information on this technique.
Let me know if I can clarify anything!
Thanks,
Jon
Hi Jon,
Thanks for the response!
I was just trying to see if there was a hacky way to replicate the facemesh functionality from Spark AR.
I have successfully controlled a head mesh from a user, but for the face I had to use the eye and mouth insets. It's a fairly creepy look, but it works well enough. You can see an example here.
Hi Michael,
Wow that's amazing! We'll definitely pass it to the engineers that this is something that you're interested in.
Can't wait to see more cool stuff.
Cheers,
Jon
I used the paper head template and a custom follow script referencing the Custom Head Bindings as the follow target to get the 3D position data from the points on the face. I too would like to see the api provide the feature points as a data stream we can consume as code.
https://www.snapchat.com/unlock/?type=SNAPCODE&uuid=a7474c51a8454436ab40633e81e52b0f&metadata=01
If you have trouble recreating the Custom tracking points manually (which i don't think i was ever able to do) you can export the element from the paper head project.