String‐Based Synthesis of Structured Shapes

• Published in: Computer graphics forum Vol. 38; no. 2; pp. 27 - 36
• Main Authors: Kalojanov, Javor, Lim, Isaak, Mitra, Niloy, Kobbelt, Leif
• Format: Journal Article
• Language: English
• Published: Oxford Blackwell Publishing Ltd 01.05.2019
• Subjects: Categories and Subject Descriptors (according to ACM CCS); Graph representations; Graphical representations; I.3.5 [Computer Graphics]: Computational Geometry and Object Modeling—Geometric algorithms, languages, and systems; Interpolation; Machine learning; Natural language processing; Repositories; Strings; Synthesis
• ISSN: 0167-7055; 1467-8659
• DOI: 10.1111/cgf.13616

We propose a novel method to synthesize geometric models from a given class of context‐aware structured shapes such as buildings and other man‐made objects. The central idea is to leverage powerful machine learning methods from the area of natural language processing for this task. To this end, we propose a technique that maps shapes to strings and vice versa, through an intermediate shape graph representation. We then convert procedurally generated shape repositories into text databases that, in turn, can be used to train a variational autoencoder. The autoencoder enables higher level shape manipulation and synthesis like, for example, interpolation and sampling via its continuous latent space. We provide project code and pre‐trained models.