3D convolution with non-linear operation. Args: inputs: 5-D tensor variable BxDxHxWxC num_output_channels: int kernel_size: a list of

Dropout layer. Args: inputs: tensor is_training: boolean tf.Variable scope: string keep_prob: float in [0,1] noise_shape: list

Fully connected layer with non-linear operation. Args: inputs: 2-D tensor BxN num_outputs: int Returns: Variable tensor of size

:param pred: BxNxC :param label: BxN :param smpw: BxN :return:

Semantic segmentation PointNet, input is B x N x 3, output B x num_class

Randomly jitter points. jittering is per point. Input: BxNx3 array, original batch of point clouds Return: BxNx3

2D max pooling. Args: inputs: 4-D tensor BxHxWxC kernel_size: a list of 2 ints stride: a list of 2 ints Returns: Variable ten

3D max pooling. Args: inputs: 5-D tensor BxDxHxWxC kernel_size: a list of 3 ints stride: a list of 3 ints Returns: Variable t

:param xyz: (b, n, 3) float :param radius: float :return: idx: (b, n, 16) int

PointNet Set Abstraction (SA) module with Multi-Scale Grouping (MSG) Input: xyz: (batch_size, ndataset, 3) TF tensor

input: batch_size * ncategory float32 batch_size * npoints float32 returns: batch_size * npoints int32

batch_pc: BxNx3

Randomly scale the point cloud. Scale is per point cloud. Input: BxNx3 array, original batch of point clouds Return:

Randomly perturb the point clouds by small rotations Input: BxNx3 array, original batch of point clouds Return: B

Randomly perturb the point clouds by small rotations Input: BxNx6 array, original batch of point clouds and point normals R

Randomly rotate the point clouds to augument the dataset rotation is per shape based along up direction Input: BxNx3 array,

Rotate the point cloud along up direction with certain angle. Input: BxNx3 array, original batch of point clouds Return:

Rotate the point cloud along up direction with certain angle. Input: BxNx3 array, original batch of point clouds Return:

Randomly rotate XYZ, normal point cloud. Input: batch_xyz_normal: B,N,6, first three channels are XYZ, last 3 all normal

Randomly rotate the point clouds to augument the dataset rotation is per shape based along up direction Input: BxNx3 array,

Randomly rotate the point clouds to augument the dataset rotation is per shape based along up direction Input: BxNx3 array,

Randomly shift point cloud. Shift is per point cloud. Input: BxNx3 array, original batch of point clouds Return:

Shuffle data and labels. Input: data: B,N,... numpy array label: B,... numpy array Return: shuffled dat

Shuffle orders of points in each point cloud -- changes FPS behavior. Use the same shuffling idx for the entire batch. Input: