In order to generate novel 3D shapes with machine learning, one must allow for interpolation. The typical approach for incorporating this creative process is to interpolate in a learned latent space so as to avoid the problem of generating unrealistic instances by exploiting the model's learned structure. The process of the interpolation is supposed to form a semantically smooth morphing. While this approach is sound for synthesizing realistic media such as lifelike portraits or new designs for everyday objects, it subjectively fails to directly model the unexpected, unrealistic, or creative. In this work, we present a method for learning how to interpolate point clouds. By encoding prior knowledge about real-world objects, the intermediate forms are both realistic and unlike any existing forms. We show not only how this method can be used to generate "creative" point clouds, but how the method can also be leveraged to generate 3D models suitable for sculpture.
@article{arxiv.1912.10787,
title = {Learned Interpolation for 3D Generation},
author = {Austin Dill and Songwei Ge and Eunsu Kang and Chun-Liang Li and Barnabas Poczos},
journal= {arXiv preprint arXiv:1912.10787},
year = {2020}
}