CSGNet: Neural Shape Parser for Constructive Solid Geometry
This addresses shape parsing and modeling for computer graphics or CAD applications, with incremental improvements in speed and detection.
The paper tackles the problem of generating programs for 2D or 3D shapes using constructive solid geometry principles, resulting in a model that is significantly faster, more effective as a shape detector compared to state-of-the-art techniques, and trainable without ground-truth annotations.
We present a neural architecture that takes as input a 2D or 3D shape and outputs a program that generates the shape. The instructions in our program are based on constructive solid geometry principles, i.e., a set of boolean operations on shape primitives defined recursively. Bottom-up techniques for this shape parsing task rely on primitive detection and are inherently slow since the search space over possible primitive combinations is large. In contrast, our model uses a recurrent neural network that parses the input shape in a top-down manner, which is significantly faster and yields a compact and easy-to-interpret sequence of modeling instructions. Our model is also more effective as a shape detector compared to existing state-of-the-art detection techniques. We finally demonstrate that our network can be trained on novel datasets without ground-truth program annotations through policy gradient techniques.