Concept Activation Vectors for Generating User-Defined 3D Shapes. (arXiv:2205.02102v1 [cs.CV])

Web: http://arxiv.org/abs/2205.02102

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 architectures
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 …

3d arxiv cv