top | item 22831088

(no title)

knotty66 | 5 years ago

Good article, thanks. BTW, this is the method Jitsi-meet uses. They also use BodyPix. https://github.com/jitsi/jitsi-meet/blob/master/react/featur...

discuss

tpetry|5 years ago

Sadly bodypic is very slow. You're only achieving 8-15fps, so any motion is very sluggish. Additionally the detection is on many cases very inaccurate: Too much or too less is detected belonging to the body so you can really only use a blur filter because a virtual background looks very strange if parts of your shoulders/hair or half an ear is missing etc.

But i am really impressed by the detection of Microsoft Teams, i would love having this quality and speed available in a browser.

TuringNYC|5 years ago

Thanks for the share @knotty66. Curious if you can discuss the technicals of this a bit? In the case of Jitsi-meet mobile apps, it seems advantageous that BodyPix models are mobile-first, but did that make sense for the desktop version as well?

I've always been disappointed that BodyPix and some similar models are mobile-first and mobile-only on TensorFlow (https://blog.tensorflow.org/2019/11/updated-bodypix-2.html) -- are these models just not used much on server-side settings? There seems to be very little documentation on doing this server side.

shrx|5 years ago

Where is the virtual background option in Jitsi? I couldn't find it.

benoliver999|5 years ago

On Jitsi Meet, in the browser, there is a menu on the bottom right. Click it and there are loads of options there including blur background.

monksy|5 years ago

It's probably an easier solution to create a processed video device

BenTheElder|5 years ago

Thanks for sharing -- With very similar settings too! (Not far from the defaults unsurprisingly).

Injecting this into a web client seems like the sweet spot effort wise.

thelastbender12|5 years ago

thank you for the link! Do you know if browser extensions can access the webcam too?