Mesh 를 다룰 때 pytorch3d, open3d 두가지의 3d 라이브러리를 많이 쓰는 편이다.
Triangle Mesh 가 있는 상황에서 Point Cloud를 뽑아내는 두 라이브러리 함수를 정리해 놓았다.
1. Open3D의 Sampling
http://www.open3d.org/docs/release/tutorial/geometry/mesh.html#Sampling
Mesh — Open3D 0.17.0 documentation
Open3D has a data structure for 3D triangle meshes called TriangleMesh. The code below shows how to read a triangle mesh from a ply file and print its vertices and triangles. The TriangleMesh class has a few data fields such as vertices and triangles. Open
www.open3d.org
pcd = mesh.sample_points_uniformly(number_of_points=500)
2. Pytorch3D '''pytorch3d.ops.sample_points_from_meshes'''
https://pytorch3d.readthedocs.io/en/latest/modules/ops.html#pytorch3d.ops.sample_points_from_meshes
pytorch3d.ops — PyTorch3D documentation
volume_features – Output volume of shape (minibatch, feature_dim, D, H, W) volume_densities: Occupancy volume of shape (minibatch, 1, D, H, W) containing the total amount of votes cast to each of the voxels.
pytorch3d.readthedocs.io
pytorch3d.ops.sample_points_from_meshes(meshes, num_samples: int = 10000, return_normals: bool = False, return_textures: bool = False)'Computer Vision' 카테고리의 다른 글
| OpenGL 공부 (0) | 2022.12.27 |
|---|---|
| BVH File Format (0) | 2022.08.12 |
