Concept Activation Vectors for Generating User-Defined 3D Shapes
We explore the interpretability of 3D geometric deep learning models in the context of Computer-Aided Design (CAD). The field of parametric CAD can be limited by the difficulty of expressing high-level design concepts in terms of a few numeric parameters.
In this paper, we use a deep learning architecture to encode high dimensional 3D shapes into a vectorized latent representation that can be used to describe arbitrary concepts. Specifically, we train a simple auto-encoder to parameterize a dataset of complex shapes.
We also test the statistical significance of the identified concepts and determine the sensitivity of a physical quantity of interest across the dataset.