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:20241205T174000
UID:siggraphasia_SIGGRAPH Asia 2024_sess136@linklings.com
SUMMARY:Generate It All: Scenes, Humans, LEGOs
DESCRIPTION:Technical Papers\n\nEach Paper gives a 10 minute presentation.
 \n\nMagicClay: Sculpting Meshes With Generative Neural Fields\n\nThe recen
 t developments in neural fields have brought phenomenal capabilities to th
 e field of shape generation, but they lack crucial properties, such as inc
 remental control --- a fundamental requirement for artistic work. Triangul
 ar meshes, on the other hand, are the representation of choice for mo...\n
 \n\nAmir Barda (Tel Aviv University), Vladimir Kim (Adobe Research), Noam 
 Aigerman (Université de Montréal), Amit Haim Bermano (Tel Aviv University)
 , and Thibault Groueix (Adobe Research)\n---------------------\nFrankenste
 in: Generating Semantic-Compositional 3D Scenes in One Tri-Plane\n\nWe pre
 sent Frankenstein, a diffusion-based framework that can generate semantic-
 compositional 3D scenes in a single pass. Unlike existing methods that out
 put a single, unified 3D shape, Frankenstein simultaneously generates mult
 iple separated shapes, each corresponding to a semantically meaningful p..
 .\n\n\nHan Yan (Shanghai Jiao Tong University); Yang Li (Tencent); Zhennan
  Wu (University of Tokyo); Shenzhou Chen, Weixuan Sun, Taizhang Shang, Wei
 zhe Liu, Tian Chen, and Xiaqiang Dai (Tencent); Chao Ma (Shanghai Jiao Ton
 g University); Hongdong Li (Australian National University); and Pan Ji (T
 encent)\n---------------------\nLearn to Create Simple LEGO Micro Building
 s\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 representations and datasets for learning coherently
 -connected bricks arrangements, as well as an immense design space that is
  combinat...\n\n\nJiahao Ge, Mingjun Zhou, and Chi-Wing Fu (Chinese Univer
 sity of Hong Kong)\n---------------------\nDIScene: Object Decoupling and 
 Interaction Modeling for Complex Scene Generation\n\nThis paper reconsider
 s 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 inputs, i.e., texts or images, to allow for flexible express
 ion of requirement; objects in the scene should be style-...\n\n\nXiao-Lei
  Li (BNRist, Department of Computer Science and Technology, Tsinghua Unive
 rsity); Haodong Li (Hong Kong University of Science and Technology, Guangz
 hou); and Hao-Xiang Chen, Tai-Jiang Mu, and Shi-Min Hu (BNRist, Department
  of Computer Science and Technology, Tsinghua University)\n---------------
 ------\nEgoAvatar: Egocentric View-Driven and Photorealistic Full-body Ava
 tars\n\nImmersive VR telepresence ideally means being able to interact and
  communicate with digital avatars that are indistinguishable from and prec
 isely reflect the behaviour of their real counterparts. The core technical
  challenge is two fold: Creating a digital double that faithfully reflects
  the real hu...\n\n\nJianchun Chen and Jian Wang (Max Planck Institute for
  Informatics; Saarbrücken Research Center for Visual Computing, Interactio
 n and AI); Yinda Zhang, Rohit Pandey, and Thabo Beeler (Google Inc.); and 
 Marc Habermann and Christian Theobalt (Max Planck Institute for Informatic
 s; Saarbrücken Research Center for Visual Computing, Interaction and AI)\n
 ---------------------\nTriHuman: A Real-time and Controllable Tri-plane Re
 presentation for Detailed Human Geometry and Appearance Synthesis\n\nCreat
 ing controllable, photorealistic, and geometrically detailed digital doubl
 es of real humans solely from video data is a key challenge in Computer Gr
 aphics and Vision, especially when real-time performance is required. Rece
 nt methods attach a neural radiance field (NeRF) to an articulated struct.
 ..\n\n\nHeming Zhu (Max Planck Institute for Informatics, Saarland Informa
 tics Campus); Fangneng Zhan (Max Planck Institute for Informatics); and Ch
 ristian Theobalt and Marc Habermann (Max Planck Institute for Informatics;
  Saarbrücken Research Center for Visual Computing, Interaction and AI)\n\n
 Registration Category: Full Access, Full Access Supporter\n\nLanguage Form
 at: English Language\n\nSession Chair: Manolis Savva (Simon Fraser Univers
 ity)
END:VEVENT
END:VCALENDAR