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:20241205T163000
DTEND;TZID=Asia/Tokyo:20241205T174000
UID:siggraphasia_SIGGRAPH Asia 2024_sess136@linklings.com
SUMMARY:Generate It All: Scenes, Humans, LEGOs
DESCRIPTION:Each Paper gives a 10 minute presentation.\n\nFrankenstein: Ge
 nerating Semantic-Compositional 3D Scenes in One Tri-Plane\n\nWe present F
 rankenstein, a diffusion-based framework that can generate semantic-compos
 itional 3D scenes in a single pass. Unlike existing methods that output a 
 single, unified 3D shape, Frankenstein simultaneously generates multiple s
 eparated shapes, each corresponding to a semantically meaningful p...\n\n\
 nHan Yan (Shanghai Jiao Tong University); Yang Li (Tencent); Zhennan Wu (U
 niversity of Tokyo); Shenzhou Chen, Weixuan Sun, Taizhang Shang, Weizhe Li
 u, Tian Chen, and Xiaqiang Dai (Tencent); Chao Ma (Shanghai Jiao Tong Univ
 ersity); Hongdong Li (Australian National University); and Pan Ji (Tencent
 )\n---------------------\nDIScene: Object Decoupling and Interaction Model
 ing for Complex Scene Generation\n\nThis paper reconsiders how to distill 
 knowledge from pretrained 2D diffusion models to guide 3D asset generation
 , in particular to generate complex 3D scenes: it should accept varied inp
 uts, i.e., texts or images, to allow for flexible expression of requiremen
 t; objects in the scene should be style-...\n\n\nXiao-Lei Li (BNRist, Depa
 rtment of Computer Science and Technology, Tsinghua University); Haodong L
 i (Hong Kong University of Science and Technology, Guangzhou); and Hao-Xia
 ng Chen, Tai-Jiang Mu, and Shi-Min Hu (BNRist, Department of Computer Scie
 nce and Technology, Tsinghua University)\n---------------------\nTriHuman:
  A Real-time and Controllable Tri-plane Representation for Detailed Human 
 Geometry and Appearance Synthesis\n\nCreating controllable, photorealistic
 , and geometrically detailed digital doubles of real humans solely from vi
 deo data is a key challenge in Computer Graphics and Vision, especially wh
 en real-time performance is required. Recent methods attach a neural radia
 nce field (NeRF) to an articulated struct...\n\n\nHeming Zhu (Max Planck I
 nstitute for Informatics, Saarland Informatics Campus); Fangneng Zhan (Max
  Planck Institute for Informatics); and Christian Theobalt and Marc Haberm
 ann (Max Planck Institute for Informatics; Saarbrücken Research Center for
  Visual Computing, Interaction and AI)\n---------------------\nEgoAvatar: 
 Egocentric View-Driven and Photorealistic Full-body Avatars\n\nImmersive V
 R telepresence ideally means being able to interact and communicate with d
 igital avatars that are indistinguishable from and precisely reflect the b
 ehaviour of their real counterparts. The core technical challenge is two f
 old: Creating a digital double that faithfully reflects the real hu...\n\n
 \nJianchun Chen and Jian Wang (Max Planck Institute for Informatics; Saarb
 rücken Research Center for Visual Computing, Interaction and AI); Yinda Zh
 ang, Rohit Pandey, and Thabo Beeler (Google Inc.); and Marc Habermann and 
 Christian Theobalt (Max Planck Institute for Informatics; Saarbrücken Rese
 arch Center for Visual Computing, Interaction and AI)\n-------------------
 --\nLearn to Create Simple LEGO Micro Buildings\n\nThis paper presents the
  first learning-based generative pipeline for effectively creating 3D LEGO
  models. This task is very challenging due to the lack of dedicated repres
 entations and datasets for learning coherently-connected bricks arrangemen
 ts, as well as an immense design space that is combinat...\n\n\nJiahao Ge,
  Mingjun Zhou, and Chi-Wing Fu (Chinese University of Hong Kong)\n--------
 -------------\nMagicClay: Sculpting Meshes With Generative Neural Fields\n
 \nThe recent developments in neural fields have brought phenomenal capabil
 ities to the field of shape generation, but they lack crucial properties, 
 such as incremental control --- a fundamental requirement for artistic wor
 k. Triangular meshes, on the other hand, are the representation of choice 
 for mo...\n\n\nAmir Barda (Tel Aviv University), Vladimir Kim (Adobe Resea
 rch), Noam Aigerman (Université de Montréal), Amit Haim Bermano (Tel Aviv 
 University), and Thibault Groueix (Adobe Research)\n\nRegistration Categor
 y: Full Access, Full Access Supporter\n\nLanguage Format: English Language
 \n\nSession Chair: Manolis Savva (Simon Fraser University)
END:VEVENT
END:VCALENDAR