Differentiable Computational Geometry for 2D and 3D machine learning
This library addresses the need for efficient, differentiable geometric operations for researchers and developers working with geometry-aware machine learning models.
This paper introduces DGAL, a C++ library providing differentiable geometric operators for primitives like lines and polygons, with GPU support. The library aims to offer high-efficiency for machine learning algorithms that incorporate geometric primitives.
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.