BSP-Net: Generating Compact Meshes via Binary Space Partitioning
BSP-Net: Generating Compact Meshes via Binary Space Partitioning
Polygonal meshes are ubiquitous in the digital 3D domain, yet they have only played a minor role in the deep learning revolution. Leading methods for learning generative models of shapes rely on implicit functions, and generate meshes only after expensive iso-surfacing routines. To overcome these challenges, we are inspired by …