---
_id: '1630'
abstract:
- lang: eng
text: 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.
acknowledgement: 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. P24600-N23).
article_number: '108'
author:
- first_name: Paul
full_name: Guerrero, Paul
last_name: Guerrero
- first_name: Stefan
full_name: Jeschke, Stefan
id: 44D6411A-F248-11E8-B48F-1D18A9856A87
last_name: Jeschke
- first_name: Michael
full_name: Wimmer, Michael
last_name: Wimmer
- first_name: Peter
full_name: Wonka, Peter
last_name: Wonka
citation:
ama: 'Guerrero P, Jeschke S, Wimmer M, Wonka P. Learning shape placements by example.
In: Vol 34. ACM; 2015. doi:10.1145/2766933'
apa: 'Guerrero, P., Jeschke, S., Wimmer, M., & Wonka, P. (2015). Learning shape
placements by example (Vol. 34). Presented at the SIGGRAPH: Special Interest Group
on Computer Graphics and Interactive Techniques, Los Angeles, CA, United States:
ACM. https://doi.org/10.1145/2766933'
chicago: Guerrero, Paul, Stefan Jeschke, Michael Wimmer, and Peter Wonka. “Learning
Shape Placements by Example,” Vol. 34. ACM, 2015. https://doi.org/10.1145/2766933.
ieee: 'P. Guerrero, S. Jeschke, M. Wimmer, and P. Wonka, “Learning shape placements
by example,” presented at the SIGGRAPH: Special Interest Group on Computer Graphics
and Interactive Techniques, Los Angeles, CA, United States, 2015, vol. 34, no.
4.'
ista: 'Guerrero P, Jeschke S, Wimmer M, Wonka P. 2015. Learning shape placements
by example. SIGGRAPH: Special Interest Group on Computer Graphics and Interactive
Techniques vol. 34, 108.'
mla: Guerrero, Paul, et al. Learning Shape Placements by Example. Vol. 34,
no. 4, 108, ACM, 2015, doi:10.1145/2766933.
short: P. Guerrero, S. Jeschke, M. Wimmer, P. Wonka, in:, ACM, 2015.
conference:
end_date: 2015-08-13
location: Los Angeles, CA, United States
name: 'SIGGRAPH: Special Interest Group on Computer Graphics and Interactive Techniques'
start_date: 2015-08-09
date_created: 2018-12-11T11:53:08Z
date_published: 2015-07-27T00:00:00Z
date_updated: 2021-01-12T06:52:07Z
day: '27'
ddc:
- '000'
department:
- _id: ChWo
doi: 10.1145/2766933
file:
- access_level: open_access
checksum: 8b05a51e372c9b0b5af9a00098a9538b
content_type: application/pdf
creator: system
date_created: 2018-12-12T10:07:49Z
date_updated: 2020-07-14T12:45:07Z
file_id: '4647'
file_name: IST-2016-576-v1+1_guerrero-2015-lsp-paper.pdf
file_size: 11902290
relation: main_file
file_date_updated: 2020-07-14T12:45:07Z
has_accepted_license: '1'
intvolume: ' 34'
issue: '4'
language:
- iso: eng
month: '07'
oa: 1
oa_version: Submitted Version
project:
- _id: 25357BD2-B435-11E9-9278-68D0E5697425
call_identifier: FWF
grant_number: P 24352-N23
name: 'Deep Pictures: Creating Visual and Haptic Vector Images'
publication_status: published
publisher: ACM
publist_id: '5525'
pubrep_id: '576'
quality_controlled: '1'
scopus_import: 1
status: public
title: Learning shape placements by example
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 34
year: '2015'
...