assign one value to all elements

Assign labels to invalid faces (whose labels are currently -1) by most of their valid neighbors. :param neighbors: [face_num,3]. Each face ca

Performs batch matrix inversion. Arguments: b_mat: the batch of matrices that should be inverted

Calculates the least-squares best-fit transform that maps corresponding points A to B in m spatial dimensions Input: A: Nxm numpy a

Calculate squared cartesian distance between points Params: point1_coord : point 1 point2_coord : point 2 ************************************

Calculate squared cartesian distance between points Params: point1_coord : point 1 point2_coord : point 2 ************************************

Evaluate a function without caching intermediate activations, allowing for reduced memory at the expense of extra compute in the backward pas

Defaults for classifier models.

If comm is provided, average all numerical stats across that comm

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

A counter for the `thop` package to count the operations in an attention operation. Meant to be used like: macs, params = thop.pr

Delete tree Params: tree : Tree struct of kd tree ************************************************/

Delete tree Params: tree : Tree struct of kd tree ************************************************/

:param gray_imgs_float32: torch tensor, [B,res,res], ranging from 0.0 to 255.0 (B indicates batch size) :return: edges: torch tensor, [B,res,

Defaults for image and classifier training.

Computes minimal distances of each point in points_src to points_tgt. Args: points_src (numpy array): source points normals_src (

Computes minimal distances of each point in points_src to points_tgt. Args: points_src (numpy array): source points normals_src (

* Create a tree node that subdivides the list of vecs from vind[first] * to vind[last]. The routine is called recursively on each sublist. *

The returned cam_RTs are used to transform from world 2 cam coordinate system. # https://zhuanlan.zhihu.com/p/561394626 target is always

Returns the nearest neighbors for point sets batchwise. Args: points_src (numpy array): source points points_tgt (numpy array): t

:param per_pixel_mask: res,res :param per_atlas_pixel_per_view_visibility: :return:

Evaluates a point cloud. Args: dist (numpy array): calculated distance thresholds (numpy array): threshold values for the F-score

Loads an image file into a (height, width, 3) uint8 ndarray. background: None or (r,g,b) [0,255]

Insert point into priority queue Params: closest_idx : index queue closest_dist : distance queue pidx : permutation index of data points

Insert point into priority queue Params: closest_idx : index queue closest_dist : distance queue pidx : permutation index of data points

Loads a previous index from a binary file. * IMPORTANT NOTE: The set of data points is NOT stored in the file, so the index object must be const

Copy model parameters into a (differently-shaped) list of full-precision parameters.

Python2 support for os.makedirs(.., exist_ok=True)

:param pc: :return:

:param atlas_img: [3,atlas_res,atlas_res] :param inpainted_imgs: [view_num, 3,res,res] :param vertices: [num_vertices, 3] :param fa

Modified from: https://github.com/AiuniAI/Unique3D/blob/main/scripts/project_mesh.py: complete_unseen_vertex_color meshes: the mesh with vert

This the transform used in shapenet dataset __getitem__. Three tasks are done: 1) Get the areas of each faces, so it can be used to sample poi

* Find all the neighbors to \a query_point[0:dim-1] within a maximum radius. * The output is given as a vector of pairs, of which the first elemen

Read binvox header. Mostly meant for internal use.

By default we use depth=12 for higher-quality reconstruction. If it's too slow to run on your device, try modify it from 12 to 8.

Stores the index in a binary file. * IMPORTANT NOTE: The set of data points is NOT stored in the file, so when loading the index object it must

:param coords: :param colors: float within range of 0-1 :param path: :return:

Saved rgb colors are uint8 ranging from 0 - 255. :param inputs: :param save_root: :return:

Search for nearest neighbour for a set of query points Params: tree : Tree struct of kd tree pa : data points pidx : permutation index of

Search for nearest neighbour for a set of query points Params: tree : Tree struct of kd tree pa : data points pidx : permutation index of

Design an actor to draw an arrow from startpoint to startpoint + vector. :param startpoint: 3D point :param vector: 3D vector :return