BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Brisbane
X-LIC-LOCATION:Australia/Brisbane
BEGIN:STANDARD
DTSTART:19920301T030000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20191203T080637Z
LOCATION:Great Hall 1&2
DTSTART;TZID=Australia/Brisbane:20191117T194700
DTEND;TZID=Australia/Brisbane:20191117T194800
UID:siggraphasia_SIGGRAPH Asia 2019_sess222_papers_345@linklings.com
SUMMARY:Data-driven Interior Plan Generation for Residential Buildings
DESCRIPTION:Technical Papers Fast-Forward \n\nData-driven Interior Plan Ge
 neration for Residential Buildings\n\nWu, Fu, Tang, Wang, Qi...\n\nWe prop
 ose a novel data-driven technique for automatically and efficiently genera
 ting floor plans for residential buildings with given boundaries. Central 
 to this method is a two-stage approach that imitates the human design proc
 ess by locating rooms first and then walls while adapting to the input bui
 lding boundary. Based on observations of the presence of the living room i
 n almost all floor plans, our designed learning network begins with positi
 oning a living room and continues by iteratively generating other rooms. T
 hen, walls are first determined by an encoder-decoder network, and then th
 ey are refined to vector representations using dedicated rules. To effecti
 vely train our networks, we construct RPLAN - a manually collected large-s
 cale densely annotated dataset of floor plans from real residential buildi
 ngs. Intensive experiments, including formative user studies and compariso
 ns, are conducted to illustrate the feasibility and efficacy of our propos
 ed approach. By comparing the plausibility of different floor plans, we ha
 ve observed that our method substantially outperforms existing methods, an
 d in many cases our floor plans are comparable to human-created ones.\n\nR
 egistration Category: Platinum Pass, Full Conference Pass, Full Conference
  One-Day Pass, Basic Conference Pass, Student One-Day Pass, Exhibitor Pass
URL:https://sa2019.conference-program.com/presentation?id=papers_345&sess=
 sess222
END:VEVENT
END:VCALENDAR

