PyTorch toolbox to work with spherical surfaces.

Note

This page is a reference documentation. It only explains the class signature, and not how to use it. Please refer to the gallery for the big picture.

class surfify.augmentation.SurfBlur(sigma, ico_order=None, vertices=None, triangles=None, neighs=None, cachedir=None)[source]¶

Bases: RandomAugmentation

An icosahedron texture Gaussian blur implementation. It uses the DiNe convolution filter for speed. The receptive field is controlled by sigma, the standard deviation of the kernel.

Init class.

Parameters:

sigma : float

sigma parameter of the gaussian filter.

ico_order : int, default None

the ico order to work with.

vertices : array (N, 3), default None

icosahedron’s vertices.

triangles : array (M, 3), default None

icosahdron’s triangles.

neighs : dict, default None

optionnaly specify the DiNe neighboors of each vertex as build with sufify.utils.neighbors, ie. a dictionary with vertices row index as keys and a dictionary of neighbors vertices row indexes organized by rings as values.

cachedir : str, default None

the optional path to cache the neighbors function output.

run(data)[source]¶

Applies the augmentation to the data.

Parameters:: data : array (N, )

input data/texture.
Returns:: data : array (N, )

blurred output data.

Examples¶

Spherical augmentations