chirikjianlab / marching-primitives Goto Github PK

There are several stl meshes in the directory 'examples', with the suffixes of 'mc' or 'mps'. I understand meshes named with 'mps' are the inputs of your algorithm, while ones with 'mc' are the outputs of your algorithm. Am I right?

Hi, thanks for your interesting work! When I visualize the example meshes produced by marching-primitives in Meshlab, it seems that the face orientations are not correct. For example:

"terataner_balrog_mps.stl":

Do you know what the reason is? How to fix it?

作者您好！我在尝试将您的工作转为python实现，但是我发现你使用了lsqnonlin函数来优化primitive的参数，我在python当中使用least_squares函数，却无法得到同样的结果，想请问您是否有所建议？

In the paper, Figure 7 shows result of indoor scene abstraction - I am trying to use this scene for HRM planner but it is missing from the repo. I am not sure if I have overlooked it. Could you let me know where I could find the mesh?

In the generated result, there is a significant overlap among primitives, such as the chair-leg and back shown in the image. The green primitive appears to be redundant. Is this expected, and how can it be adjusted?

Input:

result:

without GREEN primitive:

without CYAN:

Hi, thanks for the amazing work!
I wonder if there is an expected date for a python implementation?