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:20260817T171531Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241203T153100
DTEND;TZID=Asia/Tokyo:20241203T154300
UID:siggraphasia_SIGGRAPH Asia 2024_sess106_papers_624@linklings.com
SUMMARY:Text-guided Controllable Mesh Refinement for Interactive 3D Modeli
 ng
DESCRIPTION:Yun-Chun Chen and Selena Ling (University of Toronto); Zhiqin 
 Chen, Vladimir G. Kim, and Matheus Gadelha (Adobe Research); and Alec Jaco
 bson (University of Toronto)\n\nWe propose a novel technique for adding ge
 ometric details to an input coarse 3D mesh guided by a text prompt. Our me
 thod is composed of three stages. First, we generate a single-view RGB ima
 ge conditioned on the input coarse geometry and the input text prompt. Thi
 s single-view image generation step allows the user to pre-visualize the r
 esult and offers stronger conditioning for subsequent multi-view generatio
 n. Second, we use our novel multi-view normal generation architecture to j
 ointly generate six different views of the normal images. The joint view g
 eneration reduces inconsistencies and leads to sharper details. Third, we 
 optimize our mesh with respect to all views and generate a fine, detailed 
 geometry as output. The resulting method produces an output within seconds
  and offers explicit user control over the coarse structure, pose, and des
 ired details of the resulting 3D mesh.\n\nRegistration Category: Full Acce
 ss, Full Access Supporter\n\nLanguage Format: English Language\n\nSession 
 Chair: Yonghao Yue (Aoyama Gakuin University)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_624&sess=sess106
END:VEVENT
END:VCALENDAR