Learning shape placements by example

Paul Guerrero, Stefan Jeschke, Michael Wimmer, Peter Wonka

Research output: Chapter in Book/Report/Conference proceedingConference contribution

24 Scopus citations


We present a method to learn and propagate shape placements in 2D polygonal scenes from a few examples provided by a user. The placement of a shape is modeled as an oriented bounding box. Simple geometric relationships between this bounding box and nearby scene polygons define a feature set for the placement. The feature sets of all example placements are then used to learn a probabilistic model over all possible placements and scenes. With this model, we can generate a new set of placements with similar geometric relationships in any given scene. We introduce extensions that enable propagation and generation of shapes in 3D scenes, as well as the application of a learned modeling session to large scenes without additional user interaction. These concepts allow us to generate complex scenes with thousands of objects with relatively little user interaction. Copyright is held by the owner/author(s).
Original languageEnglish (US)
Title of host publicationACM Transactions on Graphics
PublisherAssociation for Computing Machinery (ACM)
Number of pages1
StatePublished - Jul 28 2015

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01
Acknowledged KAUST grant number(s): 62140401
Acknowledgements: This publication is based upon work supported by the KAUST Office of Competitive Research Funds (OCRF) under Award No. 62140401, the KAUST Visual Computing Center and the Austrian Science Fund (FWF) projects DEEP PICTURES (no. P24352-N23) and Data-Driven Procedural Modeling of Interiors (no. P24600N23).


Dive into the research topics of 'Learning shape placements by example'. Together they form a unique fingerprint.

Cite this