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:20250110T023312Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T163000
DTEND;TZID=Asia/Tokyo:20241205T164100
UID:siggraphasia_SIGGRAPH Asia 2024_sess136_papers_924@linklings.com
SUMMARY:Frankenstein: Generating Semantic-Compositional 3D Scenes in One T
 ri-Plane
DESCRIPTION:Technical Papers\n\nHan Yan (Shanghai Jiao Tong University); Y
 ang Li (Tencent); Zhennan Wu (University of Tokyo); Shenzhou Chen, Weixuan
  Sun, Taizhang Shang, Weizhe Liu, Tian Chen, and Xiaqiang Dai (Tencent); C
 hao Ma (Shanghai Jiao Tong University); Hongdong Li (Australian National U
 niversity); and Pan Ji (Tencent)\n\nWe present Frankenstein, a diffusion-b
 ased framework that can generate semantic-compositional 3D scenes in a sin
 gle pass. Unlike existing methods that output a single, unified 3D shape, 
 Frankenstein simultaneously generates multiple separated shapes, each corr
 esponding to a semantically meaningful part. The 3D scene information is e
 ncoded in one single tri-plane tensor, from which multiple Signed Distance
  Function (SDF) fields can be decoded to represent the compositional shape
 s. During training, an auto-encoder compresses tri-planes into a latent sp
 ace, and then the denoising diffusion process is employed to approximate t
 he distribution of the compositional scenes. Frankenstein demonstrates pro
 mising results in generating room interiors as well as human avatars with 
 automatically separated parts. The generated scenes facilitate many downst
 ream applications, such as part-wise re-texturing, object rearrangement in
  the room or avatar cloth re-targeting.\n\nRegistration Category: Full Acc
 ess, Full Access Supporter\n\nLanguage Format: English Language\n\nSession
  Chair: Manolis Savva (Simon Fraser University)
URL:https://asia.siggraph.org/2024/program/?id=papers_924&sess=sess136
END:VEVENT
END:VCALENDAR