BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240214T070311Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T090000
DTEND;TZID=Australia/Melbourne:20231214T100500
UID:siggraphasia_SIGGRAPH Asia 2023_sess148@linklings.com
SUMMARY:Texture Magic
DESCRIPTION:Technical Papers, TOG\n\nHyperDreamer: Hyper-Realistic 3D Cont
 ent Generation and Editing from a Single Image\n\n3D content creation from
  a single image is a long-standing yet highly desirable task. Recent advan
 ces introduce 2D diffusion priors, yielding reasonable results. However, e
 xisting methods are not hyper-realistic enough for post-generation usage, 
 as users cannot view, render and edit the resulting 3D...\n\n\nTong Wu and
  Zhibing Li (The Chinese University of Hong Kong, Shanghai AI Laboratory);
  Shuai Yang (Shanghai Jiao Tong University, Shanghai AI Laboratory); Pan Z
 hang (Shanghai AI Laboratory); Xingang Pan (Max Planck Institute for Infor
 matics); Jiaqi Wang (Shanghai AI Laboratory); Dahua Lin (The Chinese Unive
 rsity of Hong Kong, Shanghai AI Laboratory); and Ziwei Liu (Nanyang Techno
 logical University)\n---------------------\nJoint UV Optimization and Text
 ure Baking\n\nLevel of detail (LOD) has been widely used in interactive co
 mputer graphics. In current industrial 3D modeling pipelines, artists rely
  on commercial software to generate highly detailed models with UV maps, a
 nd then bake textures for low-poly counterparts. In these pipelines, each 
 step is performed ...\n\n\nJulian Knodt, Zherong Pan, Kui Wu, and Xifeng G
 ao (LightSpeed Studios)\n---------------------\nTexture Atlas Compression 
 Based on Repeated Content Removal\n\nOptimizing the memory footprint of 3D
  models can have a major impact on the user experiences during real-time r
 endering and streaming visualization, where the major memory overhead lies
  in the high-resolution texture data. In this work, we propose a robust an
 d automatic pipeline to content-aware, lo...\n\n\nYuzhe Luo (State Key Lab
 oratory of CAD & CG, Zhejiang University; LIGHTSPEED STUDIOS); Xiaogang Ji
 n (State Key Laboratory of CAD & CG, Zhejiang University); Zherong Pan and
  Kui Wu (LIGHTSPEED STUDIOS); Qilong Kou and Xiajun Yang (Tencent Technolo
 gy (Shenzhen) Co., LTD); and Xifeng Gao (LIGHTSPEED STUDIOS)\n------------
 ---------\nTwinTex: Geometry-aware Texture Generation for Abstracted 3D Ar
 chitectural Models\n\nCoarse architectural models are often generated at s
 cales ranging from individual buildings to scenes for downstream applicati
 ons such as Digital Twin City, Metaverse, LODs, etc. Such piece-wise plana
 r models can be abstracted as twins from 3D dense reconstructions. However
 , these models typically l...\n\n\nWeidan Xiong, Hongqian Zhang, Botao Pen
 g, Ziyu Hu, Yongli Wu, Jianwei Guo, and Hui Huang (Shenzhen University)\n-
 --------------------\nEXIM: A Hybrid Explicit-Implicit Representation for 
 Text-Guided 3D Shape Generation\n\nThis paper presents a new text-guided t
 echnique for generating 3D shapes. The technique leverages a hybrid 3D sha
 pe representation, combining the strengths of explicit and implicit repres
 entations. Specifically, the explicit stage controls the generated topolog
 y of the 3D shape and allows local mani...\n\n\nZhengzhe Liu, Jingyu Hu, a
 nd Ka-Hei Hui (The Chinese University of Hong Kong); Xiaojuan Qi (The Univ
 ersity of Hong Kong); Daniel Cohen-Or (Tel-Aviv University); and Chi-Wing 
 Fu (The Chinese University of Hong Kong)\n\nRegistration Category: Full Ac
 cess\n\nSession Chair: Lin Lu (Shandong University)
END:VEVENT
END:VCALENDAR