[wodenokoto]

Seems crazy to run an object recognition algorithm in order to decide if depths should be recorded.

I’d thought that would be heavier than just record the depths.

[brookst]

Probably a pretty light classifier on the NPU. Doesn’t even have to care about what particular object it is, just if it matches training data for “capture depth map”.

[tough]

there was recently a 64 gates NN implementation in C shared on HN that was interesting for stuff like this