eprintid: 10139847
rev_number: 12
eprint_status: archive
userid: 608
dir: disk0/10/13/98/47
datestamp: 2021-12-08 09:45:50
lastmod: 2021-12-08 09:45:50
status_changed: 2021-12-08 09:45:50
type: article
metadata_visibility: show
creators_name: Jones, RK
creators_name: Charatan, D
creators_name: Guerrero, P
creators_name: Mitra, NJ
creators_name: Ritchie, D
title: ShapeMOD: Macro Operation Discovery for 3D Shape Programs
ispublished: pub
divisions: UCL
divisions: B04
divisions: C05
divisions: F48
keywords: Shape analysis, shape synthesis, generative models, deep learning, procedural modeling, neurosymbolic models
note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
abstract: A popular way to create detailed yet easily controllable 3D shapes is via procedural modeling, i.e. generating geometry using programs. Such programs consist of a series of instructions along with their associated parameter values. To fully realize the benefits of this representation, a shape program should be compact and only expose degrees of freedom that allow for meaningful manipulation of output geometry. One way to achieve this goal is to design higher-level macro operators that, when executed, expand into a series of commands from the base shape modeling language. However, manually authoring such macros, much like shape programs themselves, is difficult and largely restricted to domain experts. In this paper, we present ShapeMOD, an algorithm for automatically discovering macros that are useful across large datasets of 3D shape programs. ShapeMOD operates on shape programs expressed in an imperative, statement-based language. It is designed to discover macros that make programs more compact by minimizing the number of function calls and free parameters required to represent an input shape collection. We run ShapeMOD on multiple collections of programs expressed in a domain-specific language for 3D shape structures. We show that it automatically discovers a concise set of macros that abstract out common structural and parametric patterns that generalize over large shape collections. We also demonstrate that the macros found by ShapeMOD improve performance on downstream tasks including shape generative modeling and inferring programs from point clouds. Finally, we conduct a user study that indicates that ShapeMOD's discovered macros make interactive shape editing more efficient.
date: 2021-08-01
date_type: published
publisher: ASSOC COMPUTING MACHINERY
official_url: https://doi.org/10.1145/3450626.3459821
oa_status: green
full_text_type: other
language: eng
primo: open
primo_central: open_green
verified: verified_manual
elements_id: 1884047
doi: 10.1145/3450626.3459821
lyricists_name: Mitra, Niloy
lyricists_id: NMITR19
actors_name: Mitra, Niloy
actors_id: NMITR19
actors_role: owner
full_text_status: public
publication: ACM Transactions on Graphics
volume: 40
number: 4
article_number: 153
pages: 16
citation:        Jones, RK;    Charatan, D;    Guerrero, P;    Mitra, NJ;    Ritchie, D;      (2021)    ShapeMOD: Macro Operation Discovery for 3D Shape Programs.                   ACM Transactions on Graphics , 40  (4)    , Article 153.  10.1145/3450626.3459821 <https://doi.org/10.1145/3450626.3459821>.       Green open access   
 
document_url: https://discovery.ucl.ac.uk/id/eprint/10139847/1/shapeMod.pdf