BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240214T070242Z
LOCATION:Darling Harbour Theatre\, Level 2 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T093000
DTEND;TZID=Australia/Melbourne:20231212T124500
UID:siggraphasia_SIGGRAPH Asia 2023_sess209_papers_257@linklings.com
SUMMARY:TwinTex: Geometry-aware Texture Generation for Abstracted 3D Archi
 tectural Models
DESCRIPTION:Technical Papers\n\nWeidan Xiong, Hongqian Zhang, Botao Peng, 
 Ziyu Hu, Yongli Wu, Jianwei Guo, and Hui Huang (Shenzhen University)\n\nCo
 arse architectural models are often generated at scales ranging from indiv
 idual buildings to scenes for downstream applications such as Digital Twin
  City, Metaverse, LODs, etc. Such piece-wise planar models can be abstract
 ed as twins from 3D dense reconstructions. However, these models typically
  lack realistic texture relative to the real building or scene, making the
 m unsuitable for vivid display or direct reference. In this paper, we pres
 ent TwinTex, the first automatic texture mapping framework to generate a p
 hoto-realistic texture for a piece-wise planar proxy. Our method addresses
  most challenges occurring in such twin texture generation. Specifically, 
 for each primitive plane, we first select a small set of photos with greed
 y heuristics considering photometric quality, perspective quality and faca
 de texture completeness. Then, different levels of line features (LoLs) ar
 e extracted from the set of selected photos to generate guidance for later
  steps. With LoLs, we employ optimization algorithms to align texture with
  geometry from local to global. Finally, we fine-tune a diffusion model wi
 th a multi-mask initialization component and a new dataset to inpaint the 
 missing region. Experimental results on many buildings, indoor scenes and 
 man-made objects of varying complexity demonstrate the generalization abil
 ity of our algorithm. Our approach surpasses state-of-the-art texture mapp
 ing methods in terms of high-fidelity quality and reaches a human-expert p
 roduction level with much less effort.\n\nRegistration Category: Full Acce
 ss, Enhanced Access, Trade Exhibitor, Experience Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=papers_257&sess=sess209
END:VEVENT
END:VCALENDAR