Makes a 3D grid. Args: bb_min (tuple): bounding box minimum bb_max (tuple): bounding box maximum shape (tuple): output s

Args: bl (float): Base length bw (float): Base width bt (float): Base thickness n_shelves (int): Number of shelve

Function to show a point cloud using meshcat. Args: mc_vis (meshcat.Visualizer): Interface to the visualizer point_cloud (

Move the end-effector in a straight line without changing the orientation. Args: delta_xyz (list or np.ndarray):

Normalize coordinate to [0, 1] for unit cube experiments. Corresponds to our 3D model Args: p (tensor): point padding (f

Normalize coordinate to [0, 1] for sliding-window experiments Args: p (tensor): point vol_range (numpy array): volume boundary

project a point to a plane

Return the quaternion inverse. Args: quat (list or np.ndarray): quaternion [x,y,z,w] (shape: :math:`[4,]`). Returns: np

Quaternion mulitplication. Args: quat1 (list or np.ndarray): first quaternion [x,y,z,w] (shape: :math:`[4,]`). q

Given a quaternion representing rotation, get the quaternion representing its inverse. Args: quaternion: Quaternions as tensor o

Convert quaternion vector to angle axis of rotation. Adapted from ceres C++ library: ceres-solver/include/ceres/rotation.h Args: qua

Convert rotations given as quaternions to axis/angle. Args: quaternions: quaternions with real part first, as tensor of

Generate random quaternions representing rotations, i.e. versors with nonnegative real part. Args: n: Number of quaternions in a

Generate random rotations as 3x3 rotation matrices. Args: n: Number of rotation matrices in a batch to return. dtype: Type t

Function to refine pointcloud registration result with a local ICP-based registration. Takes as input the result of a global registration att

Convert 3x4 rotation matrix to 4d quaternion vector This algorithm is based on algorithm described in https://github.com/KieranWynn/pyquatern

Masks part of an image that is outside of a randomly sampled rectangle Args: obj_mask (np.ndarray): Size (H, W) of boole

Setup function to instantiate the desired number of workers. Pipes and Processes set up, stored internally, and started. Args:

Visualize the pointcloud collision geometry that is being used. Args: extra_pcds (np.ndarray, optional): Other pointclouds to inc

Directly predict the relative transformation in one shot

Directly predict the relative transformation in one shot

Directly predict the relative transformation in one shot

Convert a unit quaternion to a standard form: one in which the real part is non negative. Args: quaternions: Quaternions with re

Transforms points with regard to passed camera information. Args: points (tensor): points tensor transform (tensor): transformat

Update two config dictionaries recursively. Args: dict1 (dict): first dictionary to be updated dict2 (dict): second dictionary wh

Update the defined resolution so that UNet can process. Args: reso (int): defined resolution depth (int): U-Net number of layers

Translates meshgrid of xy pixel coordinates plus depth to world coordinates.