Modified based on _PointnetSAModuleBase and PointnetSAModuleMSG with extra support for returning point indices for getting their GT votes

Calculating Average Precision

Load and parse object data

r""" Backbone network for point cloud feature learning. Based on Pointnet++ single-scale grouping network. Parameters

r"""Propigates the features of one set to another Parameters ---------- mlp : list Pointnet module parameters bn : bool

r"""Pointnet set abstrction layer with multiscale grouping Parameters ---------- npoint : int Number of features radii : list

r""" A deep neural network for 3D object detection with end-to-end optimizable hough voting. Parameters ---------- nu

r""" Groups all features Parameters ---------

Modified based on _PointnetSAModuleBase and PointnetSAModuleMSG learnable feature propagation layer.

r"""Pointnet set abstrction layer Parameters ---------- npoint : int Number of features radius : float Radius of ball

Modified based on _PointnetSAModuleBase and PointnetSAModuleMSG with extra support for returning point indices for getting their GT votes

r""" Groups with a ball query of radius Parameters --------- radius : float32 Radius of ball nsample : int32 Maxi

Calibration matrices and utils We define five coordinate system in SUN RGBD dataset camera coodinate: Z is forward, Y is