Neural nets are pattern finders. Current AP is a 2D pattern finder. It has no understanding of 3D geometry; is just knows what sort of patterns
There's a common assumption that "a neural net will learn anything, so you just need to throw more compute power and data at it". But this isn't true. 2.5D AP will *never*...
This aversion to adding hard-coded algorithms to neural nets is unjustified. We're born with all sorts of hard-coded "algorithms" in our brains, from face recognition to motion tracking...
I firmly believe that AP 4D will no longer be "matching patterns in 2D imaged". i believe it will be creating a best-fit match to 3-space,...
You would no longer just have a point cloud and labeled 2D blobs....