This site relies heavily on Javascript. You should enable it if you want the full experience. Learn more.
Manipulating Faces
about
Besides its full body/skeleton tracking capabilities the Kinect also features a dedicated face tracking functionality. With it you can easily identify individual parts (eyes, nose, mouth) of a face and then manipulate, replace, extend those using texture- or geometry-based techniques.
The download comes with 13 different demos on what you can do with the tracking data.
Note:
- Requires b32.1 + addonpack + dx11 pack
- Those demos will not work with Kinect2 out of the box but should be fairly simple to adapt once the Kinect2 nodes also features face-tracking capabilities.
download
anonymous user login
Shoutbox
~7d ago
joreg:
vvvvTv S02E01 is out: Buttons & Sliders with Dear ImGui: https://www.youtube.com/live/PuuTilbqd9w
~13d ago
joreg:
vvvvTv S02E00 is out: Sensors & Servos with Arduino: https://visualprogramming.net/blog/2024/vvvvtv-is-back-with-season-2/
~13d ago
joreg:
@fleg https://rustdesk.com/
~14d ago
fleg:
hey there! What's the best tool for remote work? Teamviewer feels terrible. Thanks!
~27d ago
joreg:
Last call: 6-session vvvv beginner course starting November 4: https://thenodeinstitute.org/courses/ws24-5-vvvv-beginners-part-i/
~1mth ago
joreg:
Missed the last meetup? You can rewatch it here: https://www.youtube.com/live/MdvTa58uxB0?si=Fwi-9hHoCmo794Ag
~1mth ago
theurbankind:
When is the next big event, like node festival ?
~1mth ago
joreg:
Introducing: Support for RPLidar devices by Slamtec: https://visualprogramming.net/blog/2024/introducing-support-for-rplidar-devices-by-slamtec/
~2mth ago
joreg:
Join us for the next vvvv meetup on Oktober 17th: https://visualprogramming.net/blog/2024/25.-vvvv-worldwide-meetup/
~2mth ago
joreg:
6 session beginner course part 2 "Deep Dive" starts January 13th: https://thenodeinstitute.org/courses/ws24-5-vvvv-beginners-part-ii/
thanks for sharing! but FullscreenQuad and some modules are missing here.
Seems good but no Kinect no ffffun... :(
@mino: i added requirements above. does that help?
@esnho: in most samples you can easily use FaceData (Kinect Microsoft Fallback) to simulate the face.
it worked! i like Celeb and UVReplace one ;)
Nice demos indeed... thanks for sharing! I have some experience programming for the Kinect but on other platforms - vvvv is quite new to me. The "makeup" patch is one that really caught my eyes. I believe it's possible to try to use another face shot as reference image, right? But how to go about editing the face markers? The patch loads them from the "face.vpe" file, right? Do we have to edit this file by hand or is there some tool that can save these points to a file?
the patch is using a PointEditor (3d Persistent) internally that allows you to manipulate the points directly. have a look at the helppatch of that node to learn how to operate it.
@joreg: I'll take a look at it... thanks!
Not sure why but my face is not being recognized, all nodes are fine, Kinect is working, maybe I am just too ugly?
Simone
SOLVED: you have to be in full sight (a least torso) of the camera, just the head isn t enough...