PointNet Set Abstraction (SA) Module Input: xyz: (batch_size, ndataset, 3) TF tensor points: (batch_size, ndataset, c

PointNet Feature Propogation (FP) Module Input:

Helper to create a Variable stored on CPU memory. Args: name: name of the variable shape: list of ints initializer: initializer for Vari

Input: points: (batch_size, ndataset, channel) float32 array, points to sample from idx: (batch_size, npoint, nsample) int32 arra

input: batch_size * ndataset * 3 float32 batch_size * npoints int32 returns: batch_size * npoints * 3 float32

returned dimension may be smaller than self.batch_size

Helper to create an initialized Variable with weight decay. Note that the Variable is initialized with a truncated normal distribution. A weight

Batch normalization on convolutional maps and beyond... Ref.: http://stackoverflow.com/questions/33949786/how-could-i-use-batch-normalization-in-te

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

Input: radius: float32, ball search radius nsample: int32, number of points selected in each ball region xyz1: (batch_siz

Input: points: (b,m,c) float32 array, known points idx: (b,n,3) int32 array, indices to known points weight: (b,n,3) floa

Input: xyz1: (b,n,3) float32 array, unknown points xyz2: (b,m,3) float32 array, known points Output: dist: (b,n,3) fl

Render point cloud to image with alpha channel. Input: points: Nx3 numpy array (+y is up direction) Output: g

Render point cloud to image with alpha channel. Input: points: Nx3 numpy array (+y is up direction) Output: g

input: int32 batch_size * ndataset * 3 float32 returns: batch_size * npoint int32

Batch normalization on 2D convolutional maps. Args: inputs: Tensor, 4D BHWC input maps is_training: boolean tf.Varialbe, true i

Input: k: int32, number of k in k-nn search xyz1: (batch_size, ndataset, c) float32 array, input points xyz2: (batch_size

Calculate the average gradient for each shared variable across all towers. Note that this function provides a synchronization point across all tower

Batch normalization on 1D convolutional maps. Args: inputs: Tensor, 3D BLC input maps is_training: boolean tf.Varialbe, true in

Batch normalization on 3D convolutional maps. Args: inputs: Tensor, 5D BDHWC input maps is_training: boolean tf.Varialbe, true

Batch normalization on FC data. Args: inputs: Tensor, 2D BxC input is_training: boolean tf.Varialbe, true indicates training ph

ops: dict mapping from string to tf ops

ops: dict mapping from string to tf ops

ops: dict mapping from string to tf ops

ops: dict mapping from string to tf ops

ops: dict mapping from string to tf ops

ops: dict mapping from string to tf ops

ops: dict mapping from string to tf ops

Classification PointNet, input is BxNx3, output Bx40

Classification PointNet, input is BxNx3, output Bx40

Classification PointNet, input is BxNx3, output Bx40

Semantic segmentation PointNet, input is BxNx3, output Bxnum_class

Classification PointNet, input is BxNx3, output Bx40

Part segmentation PointNet, input is BxNx6 (XYZ NormalX NormalY NormalZ), output Bx50

pc: BxNx3 array, return BxN pred

returned dimension may be smaller than self.batch_size

input points Nx3 numpy array (+y is up direction). return an numpy array gray image of size 500x1500.

input points Nx3 numpy array (+y is up direction). return an numpy array gray image of size 500x1500.

Demo for draw_point_cloud function

Demo for draw_point_cloud function

input is Nx3 points output is imgsize*imgsize*num_sample*3 assumes points are in range [-radius, radius] samples num_sample p

input is Nx3 points output is imgsize*imgsize*num_sample*3 assumes points are in range [-radius, radius] samples num_sample p

input is Nx3 points. output is vsize*vsize*vsize assumes points are in range [-radius, radius]

input is Nx3 points. output is vsize*vsize*vsize assumes points are in range [-radius, radius]

input is Nx3 points output is vsize*vsize*vsize*num_sample*3 assumes points are in range [-radius, radius] samples num_sample

input is Nx3 points output is vsize*vsize*vsize*num_sample*3 assumes points are in range [-radius, radius] samples num_sample

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

points is a Nx3 numpy array

points is a Nx3 numpy array

read XYZ point cloud from filename PLY file

read XYZ point cloud from filename PLY file