facebookresearch / pytorch3d

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
https://pytorch3d.org/
Other
8.7k stars 1.3k forks source link

the use of the normals_packed() #1761

Open noviceor opened 6 months ago

noviceor commented 6 months ago

In this way, it turns out that normal is None. I check the api and find there's a return value of estimate_nomals(). I'd like to know how to ues normals_packed() after 'estimate'. 屏幕截图 2024-03-17 122720 屏幕截图 2024-03-17 122323

bottler commented 6 months ago

If you want to use normals_packed() to return the value calculated by a previous estimate_nomals(), you just need to set assign_to_self=True in that call to estimate_nomals(). If you don't set that, then estimate_nomals acts as a pure function.

See https://github.com/facebookresearch/pytorch3d/blob/main/pytorch3d/structures/pointclouds.py#L1044