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:20241205T171600
DTEND;TZID=Asia/Tokyo:20241205T172800
UID:siggraphasia_SIGGRAPH Asia 2024_sess136_papers_104@linklings.com
SUMMARY:Learn to Create Simple LEGO Micro Buildings
DESCRIPTION:Jiahao Ge, Mingjun Zhou, and Chi-Wing Fu (Chinese University o
 f Hong Kong)\n\nThis paper presents the first learning-based generative pi
 peline for effectively creating 3D LEGO models. This task is very challeng
 ing due to the lack of dedicated representations and datasets for learning
  coherently-connected bricks arrangements, as well as an immense design sp
 ace that is combinatorial in nature. We approach this task by focusing on 
 creating LEGO micro buildings. Our contributions are four-fold. First, we 
 propose the LEGO semantic volume representation to encode LEGO models, con
 sidering the bricks types and bricks connections, while allowing back-prop
 agation learning. Second, we further consider the transformative nature of
  LEGO to atomize the semantic volume and formulate a generative model to l
 earn the representation. Third, we build a rich dataset of LEGO micro buil
 dings for model learning. Last, we design the progressive LEGO decoder to 
 reconstruct LEGO models from the generated representations, while ensuring
  bricks connections. We employed our pipeline to create LEGO micro buildin
 gs with a wide array of brick types, demonstrating its strong capability o
 f learning diverse micro-building styles and producing assemble-able LEGO 
 models. Further, we performed various quantitative evaluations, ablations,
  and a user study to show the compelling capability of our approach in ter
 ms of generative quality, fidelity, and diversity.\n\nRegistration Categor
 y: Full Access, Full Access Supporter\n\nLanguage Format: English Language
 \n\nSession Chair: Manolis Savva (Simon Fraser University)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_104&sess=sess136
END:VEVENT
END:VCALENDAR