SOTAVerified

Shape complexity estimation using VAE

2023-04-05Code Available0· sign in to hype

Markus Rothgaenger, Andrew Melnik, Helge Ritter

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

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.

Tasks

Reproductions