SplineGen: a generative model for B-spline approximation of unorganized points

TL;DR

SplineGen is a learning-based model that automatically determines knot placement and parameterization for B-spline approximation of unorganized points, significantly improving accuracy over traditional methods.

Contribution

It introduces a novel sequence-to-sequence generative approach that handles unorganized data without manual parameter tuning or assumptions about data order.

Findings

Achieves 10-100x higher approximation accuracy than existing methods.

Automatically determines the number and placement of knots.

Works with unorganized, unordered point data.

Abstract

This paper presents a learning-based method to solve the traditional parameterization and knot placement problems in B-spline approximation. Different from conventional heuristic methods or recent AI-based methods, the proposed method does not assume ordered or fixed-size data points as input. There is also no need for manually setting the number of knots. It casts the parameterization and knot placement problems as a sequence-to-sequence translation problem, a generative process automatically determining the number of knots, their placement, parameter values, and their ordering. Once trained, SplineGen demonstrates a notable improvement over existing methods, with a one to two orders of magnitude increase in approximation accuracy on test data.