Save a point cloud to a polygon .ply file.

Compute the mean and variance of the diffusion posterior q(x_{t-1} | x_t, x_0)

Diffuse the data (t == 0 means diffused for 1 step)

Create sinusoidal timestep embeddings. :param t: a 1-D Tensor of N indices, one per batch element. These ma

Returns the center coordinates of each cell of a 3D grid with resolution^3 cells, that is placed in the unit-cube. If clip_sphere it True it d

Returns the center coordinates of each cell of a 3D grid with resolution^3 cells, that is placed in the unit-cube. If clip_sphere it True it d

upsample points by random choice :param points: (n, 3) :param n_pts: int, > n :return:

Returns the length of the dataset.

Function: average pool voxelization (backward) Args: grad_y : grad outputs, FloatTensor[b, c, s] indices: voxel index of each point, IntTens

Function: average pool voxelization (forward) Args: features: features, FloatTensor[b, c, n] coords : coords of each point, IntTensor[b, 3,

:param ctx: :param grad_output: gradient of output, FloatTensor[B, C, R, R, R] :return: gradient of inputs, Float

:param ctx: :param grad_output: gradient of outputs, FloatTensor[B, C, N] :return: gradient of inputs, FloatTens

Computes the Coverage between two sets of point-clouds. Args: sample_pcs (numpy array SxKx3): the S point-clouds, each of K points that wi

transform: f(vertices, faces) --> transformed (vertices, faces)

transform: f(vertices, faces) --> transformed (vertices, faces)