Generative Recursive Network for Constructive Solid Geometry

Constructive solid geometry (CSG) is a technique to create a complex 3D object by using boolean operators to combine simple primitives. However, it is very challenging to obtain programs from 3D models, the inverse of the constructing process. In this Letter, the authors propose a generative recursive network for the inverse problem, which is composed of several kinds of specially designed sub-networks to get CSG programs directly from the input 3D model. Compared with previous methods, the authors' method can deal with various lengths and structures of programs, does not limit to specific primitives and can generate programs of very similar structures with the input.