get the axis-aligned bounding box of the mesh. Returns: Tuple[torch.Tensor]: the min xyz and max xyz of the mesh.

reference: GET3D, utils_3d.py, savemeshtes2 :param v_list: :param f_list: :param uv_list: :param f_mat_id_list: :param mat_im

auto calculate the vertex normals.

auto resize the mesh. Args: bound (float, optional): resizing into ``[-bound, bound]^3``. Defaults to 0.9.

auto calculate the uv coordinates. Args: cache_path (str, optional): path to save/load the uv cache as a npz file, this can avoid

Create a 1D, 2D, or 3D average pooling module.

Slicing of input with respect to the index tensor

Numpy implementation of the Frechet Distance. The Frechet distance between two multivariate Gaussians X_1 ~ N(mu_1, C_1) and X_2 ~ N(mu_2, C_2

:param gt_imgs: [N,H,W,C], uint8, 0-255 :param pred_imgs:[N,H,W,C], uint8, 0-255 :param border: :param use_sk: doesn't matter, same r

calculate SSIM the same outputs as MATLAB's img1, img2: [0, 255], [H,W,C], uint8,

:param gt_imgs: [N,H,W,C], uint8, 0-255 :param pred_imgs:[N,H,W,C], uint8, 0-255 :param border: :param use_sk: set to True, much fast

Check if all input files exist and at least one output file does not exist or is invalid. :param file_in: list of str or str :param file_

KD-tree based implementation of the Chamfer distance. Args: points1 (numpy array): first point set points2 (numpy array): second

Naive implementation of the Chamfer distance. Args: points1 (numpy array): first point set points2 (numpy array): second point se

Yield successive n-sized chunks from lst.

Computes the Intersection over Union (IoU) value for two sets of occupancy values. Args: occ1 (tensor): first set of occupancy values

Construct a sub tree over a range of data points. Params: pa : data points pidx : permutation index of data points no_dims: number of dime

Construct a sub tree over a range of data points. Params: pa : data points pidx : permutation index of data points no_dims: number of dime

Construct a tree over data points. Params: pa : data points no_dims: number of dimensions n : number of data points bsp : number of p

:param N: :param adjacency_pairs: [M,2]. adjacency_pairs[i,0] and adjacency_pairs[i,1] are neighbors :return: [N,K], indicating the K nei

Create a tree node. Params: start_idx : index of first data point to use n : number of data points ******************************************

Create a tree node. Params: start_idx : index of first data point to use n : number of data points ******************************************

Delete subtree Params: root : root node of subtree to delete ************************************************/

Delete subtree Params: root : root node of subtree to delete ************************************************/

:param img: [res,res], :param foreground_mask: :param min_for_norm: 1.0 :param max_for_norm: 3.0 :param edge_thresh: 50 # a brigh

dilate white pixels like cv2.dilate :param img_batch: [B, H, W] ,B indicate batch size. each element is either 0 or 1 :param kernel_size

Download a Google Drive file from and place it in root. Args: file_id (str): id of file to be downloaded root (str): Directory t

Evaluates a mesh. Args: mesh (trimesh): mesh which should be evaluated pointcloud_tgt (numpy array): target point clo

Evaluates a point cloud. Args: pointcloud (numpy array): predicted point cloud pointcloud_tgt (numpy array): target p

Fix camera projection matrix. This changes a camera projection matrix that maps to [0, img_size] x [0, img_size] to one that maps to [-1, 1] x

Fixes Rt camera matrix. Args: Rt (tensor): Rt camera matrix loc (tensor): location scale (float): scale

Frees all allocated memory chunks */

Get the bounding box of a set of points Params: pa : data points pidx : permutation index of data points no_dims: number of dimensions

Get the bounding box of a set of points Params: pa : data points pidx : permutation index of data points no_dims: number of dimensions

Convert box center and vectors to the corner-form :param center: :param vectors: :return: corner points and faces related to the box

Get a convolutional layer by name. # Arguments conv_name: string. The name of the convolutional layer.

Get squared distance from point to cube in specified dimension Params: dim : dimension point_coord : cartesian coordinates of point bbox :

Get squared distance from point to cube in specified dimension Params: dim : dimension point_coord : cartesian coordinates of point bbox :