A Texture Lookup Approach to Bézier Curve Evaluation on the GPU
This work addresses performance bottlenecks in GPU-based curve evaluation for graphics and computational applications, though it appears incremental as it builds on existing texture interpolation techniques.
The paper tackles the problem of evaluating Bézier curves on the GPU by proposing a texture lookup method that uses fixed-function linear texture interpolation hardware, resulting in improved performance for compute-bound workloads and extending to surfaces, volumes, and advanced curve types like B-splines and NURBS.
We present a texture-based technique for evaluating Bézier 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 Bézier 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.