A Texture Lookup Approach to B\'ezier Curve Evaluation on the GPU

TL;DR

This paper introduces a GPU texture-based method for efficient Bzier curve evaluation that leverages hardware interpolation, improving performance for complex curve and surface computations in graphics applications.

Contribution

It proposes a novel texture lookup technique for Bzier curves on GPUs, extending to surfaces, volumes, and advanced curve types, with integration of Seiler interpolation for enhanced efficiency.

Findings

Improved GPU performance in curve evaluation tasks.

Accurate approximation of Bzier curves using texture interpolation.

Effective extension to surfaces, volumes, and advanced curve types.

Abstract

We present a texture-based technique for evaluating B\'ezier curves on the GPU that leverages fixed-function linear texture interpolation hardware. By offloading curve evaluation to the texture interpolator, this approach can improve performance in compute-bound GPU workloads. The method can also be used naturally for B\'ezier surfaces and volumes and extends to advanced curve types such as B-splines, NURBS, and both integral and rational polynomials. We show how Seiler interpolation fits into this framework to improve efficiency. We also compare performance and accuracy against curves evaluated as polynomials in shader code.