Neural Shape Parsers for Constructive Solid Geometry
This work addresses the challenge of generating interpretable geometric models for applications in computer graphics and design, though it appears incremental as it builds on existing encoder-decoder methods with specific architectural enhancements.
The authors tackled the problem of parsing 2D or 3D shapes into Constructive Solid Geometry (CSG) programs, which are compact and interpretable generative models, by developing CSGNe, a deep network architecture that uses a convolutional encoder and recurrent decoder to map shapes to modeling instructions in a feed-forward manner, achieving significantly faster performance than bottom-up approaches and improved reconstruction quality with a stack-augmented encoder.
Constructive Solid Geometry (CSG) is a geometric modeling technique that defines complex shapes by recursively applying boolean operations on primitives such as spheres and cylinders. We present CSGNe, a deep network architecture that takes as input a 2D or 3D shape and outputs a CSG program that models it. Parsing shapes into CSG programs is desirable as it yields a compact and interpretable generative model. However, the task is challenging since the space of primitives and their combinations can be prohibitively large. CSGNe uses a convolutional encoder and recurrent decoder based on deep networks to map shapes to modeling instructions in a feed-forward manner and is significantly faster than bottom-up approaches. We investigate two architectures for this task --- a vanilla encoder (CNN) - decoder (RNN) and another architecture that augments the encoder with an explicit memory module based on the program execution stack. The stack augmentation improves the reconstruction quality of the generated shape and learning efficiency. Our approach is also more effective as a shape primitive detector compared to a state-of-the-art object detector. Finally, we demonstrate CSGNet can be trained on novel datasets without program annotations through policy gradient techniques.