Segmentation map to actual prediction

[simonsapiel]

Hi!

In fig 1. on your paper you display the automatic prediction compared to the actual SVG labels. How do you reproduce this since the models output is a segmentation map and running the post-processor outputs only the polygons without the actual "automatic prediction"? I assume that the result here is the floor plan after parsing it through some CAD tool, if so could you elaborate on the methods you used? Great work otherwise! @kaleaht

[ccmarkus]

The example svg labels in the paper are from our internal 2D floor plan tool.
That logic is not part of this codebase, so that is something which you would need to build yourself.

[simonsapiel]

Thanks for the response! Could you still elaborate on the part on as on how do you get the vectorized output from the model that you mentioned on "Post-processing" since the output from the post processor results in two 2-dimensional numpy arrays (pol_room_seg and pol_icon_seg)? @ccmarkus