Certainly. For example, https://storage.googleapis.com/tfjs-models/demos/posenet/cam... will run in your browser. https://github.com/CMU-Perceptual-Computing-Lab/openpose is also a decent choice for realtime pose estimation, although I'm not sure if they have a web demo anywhere.

They should work in real time. Atleast the architecture looks like end to end neural network so just like other CNN based models, this should as well work in real time after quantization etc

They showed an app like this running on a phone in laggy but real time at I/O yesterday

Yeah nowadays with post-training quantization techniques as well as things like squeezenet which is quantization aware training technique, models are becoming fairly small to be able to run on phone smoothly

Interesting, wonder what their use case was?

I can think of a couple of use cases, none of them particularly useful though. Imagine you had the pose data for the image and the pose data of someone else, even an imaginary someone else thanks to GaNs.

If it was in google IO, it will be some consumer use case probably? Althought there are a lot of commercial use cases of this technology. For example, you can train a simple classifier on top of pose which will help you record time spent on different types of activities which is useful in measuring productivity.

Dance Dance Revolution, but without the sensor mat?

https://en.wikipedia.org/wiki/Dance_Dance_Revolution

Just a fun dance recognition app to show off ML.