Shape complexity estimation using VAE

04/05/2023

∙

by   Markus Rothgaenger, et al.

∙

0

∙

share

In this paper, we compare methods for estimating the complexity of two-dimensional shapes and introduce a method that exploits reconstruction loss of Variational Autoencoders with different sizes of latent vectors. Although complexity of a shape is not a well defined attribute, different aspects of it can be estimated. We demonstrate that our methods captures some aspects of shape complexity. Code and training details will be publicly available.