Create SMPL body model :param: body_model_path (str): location to SMPL .pkl models :param body_model_type (str): smpl, smplx :param:

:param name: meter name :param val: new value to add :return: void

:param xyz1 torch tensor (B,N,1) :param xyz1 torch tensor (B,M,1) :return dist torch tensor (B,M,N)

Normalize scan on pelvis. The steps are: 1. center body on centroid of triangle waist landmark, rt asis landmark and lt asis landmark 2.

Process landmarks from .lnd file - reading file from AUX to END flags. :param landmark_path (str): path to landmark .lnd file :param scal

Create SMPL body model :param: smpl_path (str): location to SMPL .pkl models :param: gender (str): male, female or neutral :param: nu

Load landmarks from file and return the landmarks as torch tensor. Landmark file is defined in the following format: .txt extension

Load 3D scan. Accepted formats .ply, .ply.gz :param scan_path (str): path to the scan to load

Find the rotation matrix that aligns vec1 to vec2 :param vec1: A 3d "source" vector :param vec2: A 3d "destination" vector :return mat: A

Set the pose for the joint_name as set_pose in the pose parameters current_pose :param current_pose: (torch.tensor) dim (B,72) :par

Visualize point cloud with plotly

R_gt: numpy array dim (3,3) R_estim: np array dim (3,3) Returns: angle measurement in degrees

R_batch_gt: torch tensor dim (N,3,3) R_estim: torch tensor dim (3,3) Returns: angle measurement in de

Annotate 4DHumanOutfit landmarks for all subjects and actions in fit_paths. The landmarks are saved in fit_paths :param scan_paths (str)

Annotate the caesar dataset using the landmarks defined on the fitted body model. :param caesar_path (str): path to the CAESAR dataset

Create testing dataset

Create validation dataset

Create optimizer

Get paths to save and reload networks :return:

Save results in save_path as YYYY_MM_DD_HH_MM_SS folder. If continue_run is folder of type YYYY_MM_DD_HH_MM_SS, then save results in {sav

Save stats at each epoch

Add meters average in average list and keep in current_epoch the current statistics :return:

Load SMPL poses from the MOYO dataset :param data_path (str): path to the MOYO dataset :param sample_every_kth_pose (int): sample every

Find index of normalizing landmark

Create graph operation for negative log-likelihood calculation

For each point to move from points_to_move, find a random plane and move the point along the cross section of the mesh (defined with mesh_ve

Parse landamrk txt file where each line is formatted as: x_coord y_coord z_coord landmark_name :param data (List[str]) list of strings,

Parse landamrk txt file with formatting landmark_index landmark_name :param data (List[str]) list of strings, each string

input pts: np array dim N x 3 return pts: np array dim N x 4

input pts: np array dim N x 3 return pts: np array dim N x 4

Repose the unposed CAESAR scan by reposing the underlying fitted SMPL body model. Each point of the scan is reposed in the same way as its co

Reset all meters :return:

Unpose CAESAR scan by unposing the underlying fitted SMPL body model. Each point of the scan is unposed in the same way as its corresponding

Initialize weights of the network according to the given strategy :param network: torch model to initialize weights :param strategy_name

R_batch_gt: numpy array dim (N,3,3) R_estim: numpy array dim (3,3) Returns: angle measurement in degr

:return (dict): dictionary with keys: "name": name of scan "vertices": (N,3) np.array "faces": (N,3) np.a

:return (dict): dictionary with keys:

:return (dict): dictionary with keys: "name": name of scan "vertices": (N,3) np.array "faces": (N,3) np.a

:param dataset_path: (str) path to DYNA dataset :param subject_id: (str) subject id :param subject_action: (str) action perfo

:param dataset_path: (str) path to 4DHumanOutfit scans :param parameters_path: (str) path to the directory where the already

Dataset defined with a .npz file or folder with .npz files The .npz files are data points of subjects with landmarks and measurements

Extension of the NPZ dataset that allows for augmentation of the landmarks :param dataset_path: (str) path to the .npz file or folde

cfg: config dictionary with :param data_dir (str): path to caesar dataset :param load_countries (str or list): countries to l

:param caesar_dir: (str) path to caesar dataset :param fitted_bm_dir: (str) path to SMPL param fits to CAESAR dataset :param