Questions about input data and how to get primitive indexs of each point

[LuciusPennyworth]

Hi jingwei, I am currently following your wonderful work. After running your code, I have some questions about the dataset.

First, in dataset.py, I consider F and SF as faces and the primitive type of faces. But the numbers of F is much more than xyz_origin which is strange. So, what's the meaning of F and SF and why don't just use primitive type and primitive idx of each point, just like ParseNet and others? xyz_origin, normal, boundary, F, SF = data['V'], data['N'], data['B'], data['F'], data['S']

Second, also in dataset.py, I consider the variable 'semantic' as the primitive type of each point. And this variable also be packed into batch['semantic_gt'] as ground truth. semantics = np.zeros((xyz_origin.shape[0]), dtype='int32') semantics[F[:, 0]] = SF; semantics[F[:, 1]] = SF; semantics[F[:, 2]] = SF But when I visualize one point cloud and add colors to each point according to 'semantics', the visualization results and color_map are blow: The orange part seems incorrect which a spline is labeled as a plane. And the cyclinder in purple also is labeled as cone.

color_map={

    # (key:value  represents  primitiveType: rgb)
    1: [255, 127, 14],  # plane         orange
    3: [148, 103, 189],  # cone        purple
    4: [31, 119, 180],  # cyclinder   blue
    5: [44, 160, 44],  # sphere         green

    2: [220,220,220],  # open b-spline  gray
    8: [220,220,220],  # open b-spline  gray
    0: [220,220,220],  # closed b-spline  gray
    6: [220,220,220],  # closed b-spline  gray
    7: [220,220,220],  # closed b-spline  gray
    9: [220,220,220],  # closed b-spline  gray
}

So, my question is, did the [1,3,4,5] represents to [plane, cone, cyclinder, sphere] separately just like ParseNet? Or you may use other representation?

Thanks in advance for your reply and code!

[guohaoxiang]

I have the same question.

[prathebaselva]

LuciusPennyworth

Is it possible to share the data using some other cloud drive other than Baidu? Could not get it downloaded from the link given in the script file.