So, I am doing this project where I have lets say a bunch of points. Each of those points can have a different number of RGB values. So lets say point 1 might have 30 RGB values, point 2 might have 500 rgb values. The idea is I want to decide something based on the variances those RGB values have across them. The idea has more than this to it, however I wanted to state it here in simple terms. I am kind of at a loss as to how I would fit this varying size of data as input and what architecture should I be approaching towards. Any clue or pointer would help.

  • 1
    $\begingroup$ When you say points, do you mean vectors? Matrices? Images? $\endgroup$ – Andreas Storvik Strauman Jul 28 '19 at 19:40
  • $\begingroup$ By points I mean a single (x,y,z) of a bunch of (x,y,z) of the point cloud. Say, 13.5, 14.5, 20 is a single point. It might have 30 RGB values depending on how it looked in the various cameras. $\endgroup$ – stannis Aug 7 '19 at 15:14

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.