Convert points in camera coordinate to lidar coordinate. Args: points (np.ndarray, shape=[N, 3]): Points in camera coordinate. r_

Input: points: input points data, [B, N, C] idx: sample index data, [B, S, [K]] Return: new_points:, indexed points d

Waymo segmentation label: TYPE_UNDEFINED = 0; TYPE_CAR = 1; TYPE_TRUCK = 2; TYPE_BUS = 3;

Convert kitti locations, dimensions and angles to corners. format: center(xy), dims(xy), angles(clockwise when positive) Args: center

Convert kitti locations, dimensions and angles to corners. Args: centers (np.ndarray): Locations in kitti label file with shape (N, 3).

Convert range images to point cloud. Args: frame (:obj:`Frame`): Open dataset frame. range_images (dict): Mapping fro

Generate relative box corners based on length per dim and origin point. Args: dims (np.ndarray, shape=[N, ndim]): Array of length per dim

Args: crop_mask: (n,) (bool) True means not crop. label: (n,) (bool) mode: 'PR' or 'IOU'

Used for tensorboard visualization

Check points is in 3d convex polygons. Args: points (np.ndarray): Input points with shape of (num_points, 3). polygon_surfaces (n

Args: points (np.ndarray): Input points with shape of (num_points, 3). polygon_surfaces (np.ndarray): Polygon surfaces with shape

Convert transformation matrix in Cartesian coordinates to homogeneous format. Args: mat (np.ndarray): Transformation matr

Center to minmax. Args: centers (np.ndarray): Center points. dims (np.ndarray): Dimensions. origin (list or array or floa

Convert action for single file. Args: file_idx (int): Index of the file to be converted.

convert 3d box corners from corner function above to surfaces that normal vectors all direct to internal. Args: corners (np.ndarray):

Convert 3d box corners from corner function above to surfaces that normal vectors all direct to internal. Args: corners (np.ndarray):

Create info file of waymo dataset. Given the data created by mmdetection3d, generate scene flow data. Args: data_path (s

Create folder for data preprocessing.

Convert depth map to points. Args: depth (np.array, shape=[H, W]): Depth map which the row of [0~`trunc_pixel`] are truncated

Due to the similarity of adjacent frames, it is preferred to search the neighborhood.

Generate crop parameters for remove ground.

Create scene flow dataset. Args:

Get frustum corners in camera coordinates. Args: bbox_image (list[int]): box in image coordinates. C (np.ndarray): Intrinsics.

Get info of all frames: { [optional]points: [N, 3+] point cloud [optional, for kitti]image: { frame_idx: ...

Limit the value into a period for periodic function. Args: val (np.ndarray): The value to be converted. offset (float, optional):

Args: path: Returns: pc1: ndarray (N, 3) np.float32 pc2: ndarray (N, 3) np.float32

Project points in camera coordinates to image coordinates. Args: points_3d (np.ndarray): Points in shape (N, 3) proj_mat (np.ndar

Split projection matrix of kitti. P = C @ [R|T] C is upper triangular matrix, so we need to inverse CR and use QR stable for all kitti ca

Read .flo file in Middlebury format

Rotation 2d points based on origin point clockwise when angle positive. Args: points (np.ndarray): Points to be rotated with shape \

Rotate points in specific axis. Args: points (np.ndarray, shape=[N, point_size, 3]]): angles (np.ndarray, shape=[N]]): ax

Parse and save the calibration data. Args: frame (:obj:`Frame`): Open dataset frame proto. file_idx (int): Current fi

Parse and save the images in png format. Args: frame (:obj:`Frame`): Open dataset frame proto. file_idx (int): Curren

Parse and save the label data in txt format. The relation between waymo and kitti coordinates is noteworthy: 1. x, y, z correspond to

Parse and save the lidar data in psd format. Args: frame (:obj:`Frame`): Open dataset frame proto. file_idx (int): Cu

Parse and save the pose data. Note that SDC's own pose is not included in the regular training of KITTI dataset. KITTI raw dataset co

Calculate Euclid distance between each two points. src^T * dst = xn * xm + yn * ym + zn * zm； sum(src^2, dim=-1) = xn*xn + yn*yn + zn*zn;

Args: polygon_surfaces (np.ndarray): Polygon surfaces with shape of [num_polygon, max_num_surfaces, max_num_points_of_surfac

Peform validation using the KITTI-2015 (train) split

Peform validation using the Things (test) split

Peform validation using the KITTI-2015 (train) split