eprintid: 10083155 rev_number: 18 eprint_status: archive userid: 608 dir: disk0/10/08/31/55 datestamp: 2019-10-15 14:42:43 lastmod: 2021-10-10 23:11:24 status_changed: 2019-10-15 14:42:43 type: article metadata_visibility: show creators_name: Kalojanov, J creators_name: Lim, I creators_name: Mitra, N creators_name: Kobbelt, L title: String-Based Synthesis of Structured Shapes ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F48 note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. 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. date: 2019-05 date_type: published publisher: WILEY official_url: https://doi.org/10.1111/cgf.13616 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1666549 doi: 10.1111/cgf.13616 lyricists_name: Mitra, Niloy lyricists_id: NMITR19 actors_name: Mitra, Niloy actors_id: NMITR19 actors_role: owner full_text_status: public publication: Computer Graphics Forum volume: 38 number: 2 pagerange: 27-36 pages: 10 issn: 1467-8659 citation: Kalojanov, J; Lim, I; Mitra, N; Kobbelt, L; (2019) String-Based Synthesis of Structured Shapes. Computer Graphics Forum , 38 (2) pp. 27-36. 10.1111/cgf.13616 <https://doi.org/10.1111/cgf.13616>. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10083155/1/string2shape.pdf