Florian Echtler

Ah, that does sound like SSE and friends could do a good job speeding things up. I guess the most portable way to do that is using gcc intrinsics?

Found this just now: https://developers.google.com/ml-kit/vision/selfie-segmentation Seems to be Apache-licensed (for now), problem is actually getting the model file, which is buried inside the MLKit runtime.

Update: you can get the AAR file (which is just a Zip) via https://mvnrepository.com/artifact/com.google.mlkit/segmentation-selfie/16.0.0-beta1 - and there is indeed a .tflite file in there, that should be worth a try...

Yes, quick-and-dirty implementation in https://github.com/floe/deepbacksub/commit/24dc33fcf1bc562754ce79e0bc61e8343ffbd47b - seems to be a candidate for new default model?

Three really quick-and-dirty (again) screenshots, in the order: new selfie model, Meet model, deeplabv3+.   

Oh, good to know, should we put this in a Troubleshooting section in the README maybe?

Mmh, try giving the full path to backscrub (`... -m /usr/local/share/backscrub/models/segm_full_v679.tflite`).

@BenBE @phlash side note: should we use the selfiesegmentation model as default for the next release?

Somewhat addressed by the most recent merge from experimental, please test.

I think this here would fit the bill: https://google.github.io/mediapipe/solutions/hands.html