423A35C7/pytorch3d
1
0
Fork 0
mirror of https://github.com/facebookresearch/pytorch3d.git synced 2025-08-02 20:02:49 +08:00
Code Issues Packages Projects Releases Wiki Activity

Restrict import of ops from Pointclouds

Browse Source 
Summary: Move to a local import for calculating pointcloud normals, similar to _compute_face_areas_normals on Meshes.

Reviewed By: theschnitz

Differential Revision: D24695260

fbshipit-source-id: 9e1eb5d15017975b8c4f4175690cc3654f38d9a4
This commit is contained in:
Jeremy Reizenstein 2020-11-04 03:59:15 -08:00 committed by Facebook GitHub Bot
parent 039e02601d
commit e9a26f263a
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
pytorch3d/ops/points_normals.py
View File

@ -20,7 +20,7 @@ def estimate_pointcloud_normals(
Estimates the normals of a batch of `pointclouds`. Estimates the normals of a batch of `pointclouds`.
The function uses `estimate_pointcloud_local_coord_frames` to estimate The function uses `estimate_pointcloud_local_coord_frames` to estimate
the normals. Please refer to this function for more detailed information. the normals. Please refer to that function for more detailed information.
Args: Args:
**pointclouds**: Batch of 3-dimensional points of shape **pointclouds**: Batch of 3-dimensional points of shape

4
pytorch3d/structures/pointclouds.py
View File

@ -2,7 +2,6 @@
import torch import torch
from .. import ops
from . import utils as struct_utils from . import utils as struct_utils
@ -890,7 +889,7 @@ class Pointclouds(object):
them to the internal tensors `self._normals_list` and `self._normals_padded` them to the internal tensors `self._normals_list` and `self._normals_padded`
The function uses `ops.estimate_pointcloud_local_coord_frames` The function uses `ops.estimate_pointcloud_local_coord_frames`
to estimate the normals. Please refer to this function for more to estimate the normals. Please refer to that function for more
detailed information about the implemented algorithm. detailed information about the implemented algorithm.
Args: Args:
@ -908,6 +907,7 @@ class Pointclouds(object):
[1] Tombari, Salti, Di Stefano: Unique Signatures of Histograms for [1] Tombari, Salti, Di Stefano: Unique Signatures of Histograms for
Local Surface Description, ECCV 2010. Local Surface Description, ECCV 2010.
""" """
from .. import ops
# estimate the normals # estimate the normals
normals_est = ops.estimate_pointcloud_normals( normals_est = ops.estimate_pointcloud_normals(