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:20250110T023313Z
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:Technical Papers\n\nAleksander Plocharski (Warsaw University o
 f Technology, IDEAS NCBR); Jan Swidzinski (IDEAS NCBR); Joanna Porter-Sobi
 eraj (Warsaw University of Technology); and Przemyslaw Musialski (New Jers
 ey Institute of Technology, IDEAS NCBR)\n\nWe introduce a neuro-symbolic t
 ransformer-based model that converts flat, segmented facade structures int
 o procedural definitions using a custom-designed split grammar. To facilit
 ate this, we first develop a simple split grammar tailored for architectur
 al facades and then generate a dataset comprising of facades alongside the
 ir corresponding procedural representations. This dataset is used to train
  our transformer model to convert segmented, flat facades into the procedu
 ral language of our grammar. During inference, the model applies this lear
 ned transformation to new facade segmentations, providing a procedural rep
 resentation that users can adjust to generate varied facade designs. This 
 method not only automates the conversion of static facade images into dyna
 mic, editable procedural formats but also enhances the design flexibility,
  allowing for easy modifications and variations by architects and designer
 s. Our approach sets a new standard in facade design by combining the prec
 ision of procedural generation with the adaptability of neuro-symbolic lea
 rning.\n\nRegistration Category: Full Access, Full Access Supporter\n\nLan
 guage Format: English Language\n\nSession Chair: Maria Larsson (University
  of Tokyo)
URL:https://asia.siggraph.org/2024/program/?id=papers_817&sess=sess142
END:VEVENT
END:VCALENDAR