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*num_sample*3 assumes points are in range [-radius, radius] samples num_sample

Convert predictions to OBB parameters (eight corner points) Args: end_points: dict {point_clouds, center, heading_scores, hea

project point cloud from depth coord to camera coordinate Input: (N,3) Output: (N,3)

points is a Nx3 numpy array

if string s represents an int.

Rotation about the y-axis.

Rotation about the y-axis. t: (x1,x2,...xn) return: (x1,x2,...,xn,3,3)

Rotation about the Z-axis.

Log a scalar variable.

Numpy function for softmax

Visualize oriented bounding box ground truth pc: (N,3) label: (K,3) K == MAX_NUM_OBJ mask: (K,) angle_classes: (K,) angle_residu

Visualize oriented bounding box ground truth pc: (N,3) label: (K,3) K == MAX_NUM_OBJ mask: (K,) angle_classes: (K,) angle_residu

Visualize point votes and point votes mask labels pc: (N,3 or 6), point_votes: (N,9), point_votes_mask: (N,)

Visualize point votes and point votes mask labels pc: (N,3 or 6), point_votes: (N,9), point_votes_mask: (N,)

ap = voc_ap(rec, prec, [use_07_metric]) Compute VOC AP given precision and recall. If use_07_metric is true, uses the VOC 07 11 point met

vol is occupancy grid (value = 0 or 1) of size vsize*vsize*vsize return Nx3 numpy array.

Create lines represented as cylinders connecting pairs of 3D points Args: pcl: (N x 2 x 3 numpy array): N pairs of xyz pos

Export oriented (around Z axis) scene bbox to meshes Args: scene_bbox: (N x 7 numpy array): xyz pos of center and 3 lengths (dx,dy,dz)

Returns a dict with following keys: point_clouds: (N,3+C) center_label: (MAX_NUM_OBJ,3) for GT box center XYZ

Returns a dict with following keys: point_clouds: (N,3+C) center_label: (MAX_NUM_OBJ,3) for GT box center XYZ

Returns a dict with following keys: point_clouds: (N,3+C) scan_idx: int scan index in scan_names list

Returns a dict with following keys: point_clouds: (N,3+C) center_label: (MAX_NUM_OBJ,3) for GT box center XYZ

Returns a dict with following keys: point_clouds: (N,3+C) scan_idx: int scan index in scan_names list

Create a summary writer logging to log_dir.

Args: ap_iou_thresh: float between 0 and 1.0 IoU threshold to judge whether a prediction is positive.

Votes generation from seed point features. Args: vote_facotr: int number of votes generated from each seed point

Args: batch_pred_corners_3d: ndarray (num_batch, num_proposals, 8, 3) predicted bounding boxes (represented by 8 corner poin

Convert continuous angle to discrete class [optinal] also small regression number from class center angle to current angle.

r""" Parameters ---------- grad_out : torch.Tensor (B, c, n) tensor with gradients of ouputs Returns

r""" Parameters ---------- grad_out : torch.Tensor (B, C, npoint, nsample) tensor of the gradients of the output

Compute 2D bounding box IoU. Input: box1: tuple of (xmin,ymin,xmax,ymax) box2: tuple of (xmin,ymin,xmax,ymax) Output:

Input: batch_corners1: numpy array (n,8,3), assume up direction is negative Y batch_corners2: numpy array (m,8,3), assume up dire

check if a predicted corners3d is a valid cube 6 -------- 5 /| /| 7 -------- 4 . | | | |

Takes an object and a projection matrix (P) and projects the 3d bounding box into the image plane. Returns: corners_2d: (

Takes an object and a projection matrix (P) and projects the 3d object orientation vector into the image plane. Returns: