search

yewzijian / RPMNet

RPM-Net: Robust Point Matching using Learned Features (CVPR2020)
MIT License
344 stars 59 forks source link

Normal Problem #34

Open JarvisLee0423 opened 1 year ago

JarvisLee0423 commented 1 year ago

Hi, after I test your great work, I got one question about the normal, due to I don't find any description of the normal from the official webset of the modelnet40. I have three questions about the normals: 1) Is the normal of each vertex computed from its 64 neighbourhoods which inside the sphere region with 0.3 radius? 2) Are all the normals normalized? 3) Are the orientations of all the normals consistent? If yes, whether they are orienting to the mass center of the mesh?

Meanwhile, if I want to test the network with my own dataset, what kind of preprocessing should I do for the normals? Or, can I just use the open3d's function esitimate_normal to be the input normal?

yewzijian commented 1 year ago

Normals are provided by in the ModelNet dataset, and should be normalized and pointing in the correct direction (i.e. out of the surface).

Yes you open3d's normal estimation seems like a good choice.

JarvisLee0423 commented 1 year ago

Thanks a lot! And for another question, I saw in your original code, you set the rotation limitation in the range from 0 to 45 degree. So, I want to know, did you do any experiments to ensure whether the generalization of the model can handle the rotation angle which is larger than the 45 degree or not, like any angle from 60 to 180 degree. Or, do I have to retrain the model with a larger rotation limitation range?