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:20260817T171532Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T164100
DTEND;TZID=Asia/Tokyo:20241205T165300
UID:siggraphasia_SIGGRAPH Asia 2024_sess136_papers_306@linklings.com
SUMMARY:DIScene: Object Decoupling and Interaction Modeling for Complex Sc
 ene Generation
DESCRIPTION:Xiao-Lei Li (BNRist, Department of Computer Science and Techno
 logy, Tsinghua University); Haodong Li (Hong Kong University of Science an
 d Technology, Guangzhou); and Hao-Xiang Chen, Tai-Jiang Mu, and Shi-Min Hu
  (BNRist, Department of Computer Science and Technology, Tsinghua Universi
 ty)\n\nThis paper reconsiders how to distill knowledge from pretrained 2D 
 diffusion models to guide 3D asset generation, in particular to generate c
 omplex 3D scenes: it should accept varied inputs, i.e., texts or images, t
 o allow for flexible expression of requirement; objects in the scene shoul
 d be style-consistent and decoupled with clearly modeled interactions, ben
 efiting downstream tasks. \n We propose DIScene, a novel method for this t
 ask.It represents the entire 3D scene with a learnable structured scene gr
 aph: each node explicitly models an object with its appearance, textual de
 scription, transformation, geometry as a mesh attached with surface-aligne
 d Gaussians;  the graph's edges model object interactions. \n With this ne
 w representation, objects are optimized in the canonical space and interac
 tions between objects are optimized by object-aware rendering to avoid wro
 ng back-propagation. \n Extensive experiments demonstrate the significant 
 utility  and superiority of our approach and that DIScene can greatly faci
 litate 3D content creation tasks.\n\nRegistration Category: Full Access, F
 ull 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_306&sess=sess136
END:VEVENT
END:VCALENDAR