Differentiable Computational Geometry for 2D and 3D machine learning

TL;DR

This paper introduces DGAL, a high-performance, differentiable geometry library for 2D and 3D primitives, optimized for machine learning applications with GPU support.

Contribution

It presents a header-only, templated C++ library with differentiable operators for geometric primitives, enhancing efficiency in geometry-based machine learning tasks.

Findings

DGAL achieves high efficiency in geometric computations.

The library supports GPU acceleration for differentiable operators.

Benchmark results show competitive performance against existing implementations.

Abstract

With the growth of machine learning algorithms with geometry primitives, a high-efficiency library with differentiable geometric operators are desired. We present an optimized Differentiable Geometry Algorithm Library (DGAL) loaded with implementations of differentiable operators for geometric primitives like lines and polygons. The library is a header-only templated C++ library with GPU support. We discuss the internal design of the library and benchmark its performance on some tasks with other implementations.