torchcurves.functional

Normalization

Low-level helpers for mapping inputs to bounded intervals. Most users should prefer input_map and torchcurves.maps on the module API.

clamp(x[, scale, out_min, out_max])	Clamp values in a tensor to a specified range.
rational(x[, scale, out_min, out_max])	Normalize values using the "Legendre Rational Functions" [1] normalization method.
arctan(x[, scale, out_min, out_max])	Normalize values using the "arctan" normalization method.

Parametrized curves

Vectorized parametric curve evaluation functions.

bspline_curves	Evaluate multiple B-Spline curves, each with its own control points, sharing the same knots and degree.
legendre_curves	Evaluate curves parametrized by Legendre polynomials.

Utilities

uniform_augmented_knots

Generate an augmented knot vector with uniform spacing in [-1, 1] for B-spline curves.