kaolin.rep.TriangleMesh

class TriangleMesh(vertices: torch.Tensor, faces: torch.Tensor, uvs: torch.Tensor, face_textures: torch.Tensor, textures: torch.Tensor, edges: torch.Tensor, edge2key: dict, vv: torch.Tensor, vv_count: torch.Tensor, vf: torch.Tensor, vf_count: torch.Tensor, ve: torch.Tensor, ve_count: torch.Tensor, ff: torch.Tensor, ff_count: torch.Tensor, ef: torch.Tensor, ef_count: torch.Tensor, ee: torch.Tensor, ee_count: torch.Tensor)

Abstract class to represent 3D Trianlge meshes.

compute_adjacency_matrix_full()

Calcualtes a binary adjacency matrix for a mesh.

Returns

binary adjacency matrix

Return type

(torch.Tensor)

Example

>>> mesh = TriangleMesh.from_obj('model.obj')
>>> adj_info = mesh.compute_adjacency_matrix_full()
>>> neighborhood_sum = torch.mm( adj_info, mesh.vertices)

compute_adjacency_matrix_sparse()

Calcualtes a sparse adjacency matrix for a mess

Returns

sparse adjacency matrix

Return type

(torch.sparse.Tensor)

Example

>>> mesh = Mesh.from_obj('model.obj')
>>> adj_info = mesh.compute_adjacency_matrix_sparse()
>>> neighborhood_sum = torch.sparse.mm(adj_info, mesh.vertices)

compute_face_normals()

Compute normals for each face in the mesh.

compute_vertex_normals()

Compute vertex normals for each mesh vertex.

load_tensors(enable_adjacency: bool = False)

Loads the tensor information of the mesh from a saved numpy array.

Parameters

filename – Path of the file to load the file from.

Example

>>> mesh = TriangleMesh.load_tensors('mesh.npy')

sample(num_samples: int, eps: float = 1e-10)

Uniformly samples the surface of a mesh.

Parameters

• num_samples (int) – number of points to sample

• eps (float) – a small number to prevent division by zero for small surface areas.

Returns

(torch.Tensor, torch.Tensor) uniformly sampled points and

the face idexes which each point corresponds to.

Example

>>> points, chosen_faces = mesh.sample(10)
>>> points
tensor([[ 0.0293,  0.2179,  0.2168],
        [ 0.2003, -0.3367,  0.2187],
        [ 0.2152, -0.0943,  0.1907],
        [-0.1852,  0.1686, -0.0522],
        [-0.2167,  0.3171,  0.0737],
        [ 0.2219, -0.0289,  0.1531],
        [ 0.2217, -0.0115,  0.1247],
        [-0.1400,  0.0364, -0.1618],
        [ 0.0658, -0.0310, -0.2198],
        [ 0.1926, -0.1867, -0.2153]])
>>> chosen_faces
tensor([ 953,  38,  6, 3480,  563,  393,  395, 3309, 373, 271])

save_mesh(filename: str)

Save a mesh to a wavefront .obj file format

Parameters

filename (str) – target filename