String‐Based Synthesis of Structured Shapes. (7th June 2019)

• Record Type: Journal Article
• Authors: Kalojanov, Javor; Lim, Isaak; Mitra, Niloy; Kobbelt, Leif
• Is Part Of: Computer graphics forum. Volume 38:Number 2(2019)
• Page Start: 27
• Page End: 36
• Publication Date: 2019-06-07
• Subjects: Categories and Subject Descriptors (according to ACM CCS) -- I.3.5 [Computer Graphics]: Computational Geometry and Object Modeling—Geometric algorithms, languages, and systems; Computer graphics -- Periodicals; 006.605
• DOI: 10.1111/cgf.13616
• Languages: English
• ISSNs: 0167-7055

Abstract

Abstract: 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.