BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T171535Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T104500
DTEND;TZID=Asia/Tokyo:20241206T105600
UID:siggraphasia_SIGGRAPH Asia 2024_sess142_papers_817@linklings.com
SUMMARY:FaçAID: A Transformer Model for Neuro-Symbolic Facade Reconstructi
 on
DESCRIPTION:Aleksander Plocharski (Warsaw University of Technology, IDEAS 
 NCBR); Jan Swidzinski (IDEAS NCBR); Joanna Porter-Sobieraj (Warsaw Univers
 ity of Technology); and Przemyslaw Musialski (New Jersey Institute of Tech
 nology, IDEAS NCBR)\n\nWe introduce a neuro-symbolic transformer-based mod
 el that converts flat, segmented facade structures into procedural definit
 ions using a custom-designed split grammar. To facilitate this, we first d
 evelop a simple split grammar tailored for architectural facades and then 
 generate a dataset comprising of facades alongside their corresponding pro
 cedural representations. This dataset is used to train our transformer mod
 el to convert segmented, flat facades into the procedural language of our 
 grammar. During inference, the model applies this learned transformation t
 o new facade segmentations, providing a procedural representation that use
 rs can adjust to generate varied facade designs. This method not only auto
 mates the conversion of static facade images into dynamic, editable proced
 ural formats but also enhances the design flexibility, allowing for easy m
 odifications and variations by architects and designers. Our approach sets
  a new standard in facade design by combining the precision of procedural 
 generation with the adaptability of neuro-symbolic learning.\n\nRegistrati
 on Category: Full Access, Full Access Supporter\n\nLanguage Format: Englis
 h Language\n\nSession Chair: Maria Larsson (The University of Tokyo)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_817&sess=sess142
END:VEVENT
END:VCALENDAR