BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250522T212948Z
LOCATION:Mile High 2A
DTSTART;TZID=America/Denver:20240729T104500
DTEND;TZID=America/Denver:20240729T121500
UID:siggraph_SIGGRAPH 2024_sess140@linklings.com
SUMMARY:Generative 3D Geometry
DESCRIPTION:Spice-E: Structural Priors in 3D Diffusion Using Cross-Entity 
 Attention\n\nText-to-3D diffusion models can generate high-quality 3D shap
 es in seconds, but they are hard to control. In this work we introduce Spi
 ce-E — a neural network that adds structural guidance to 3D diffusion mode
 ls, allowing for solving a variety of 3D to 3D tasks with SOTA performance
 .\n\n\nEtai Sella, Gal Fiebelman, Noam Atia, and Hadar Averbuch-Elor (Tel 
 Aviv University)\n---------------------\nBlockFusion: Expandable 3D Scene 
 Generation Using Latent Tri-plane Extrapolation\n\nBlockFusion is a 3D dif
 fusion-based model that generates and expands 3D scenes using unit blocks.
  The denoising diffusion process allows high-quality and diverse scene gen
 eration and auto-regressive scene expansion. BlockFusion generates large, 
 high-quality 3D scenes for indoor and outdoor scenarios...\n\n\nZhennan Wu
  (University of Tokyo); Yang Li (Tencent); Han Yan (Shanghai Jiao Tong Uni
 versity); Taizhang Shang, Weixuan Sun, and Senbo Wang (Tencent); Ruikai Cu
 i (Australian National University); Weizhe Liu (Tencent); Hiroyuki Sato (N
 ational Institute of Informatics, Japan; University of Tokyo); and Hongdon
 g Li and Pan Ji (Tencent)\n---------------------\nDreamFont3D: Personalize
 d Text-to-3D Artistic Font Generation\n\nThis paper presents a novel text-
 to-3D font generation model. It allows text prompt to describe 3D font sty
 les, and script-generated font masks or hand-drawn font layouts to constra
 in the 3D font structure at multi-views, achieving stunning 3D representat
 ion of artistic font and the control of local...\n\n\nXiang Li (Shandong U
 niversity); Lei Meng (Shandong University, Shandong Research Institute of 
 Industrial Technology); and Lei Wu, Manyi Li, and Xiangxu Meng (Shandong U
 niversity)\n---------------------\nCoin3D: Controllable and Interactive 3D
  Assets Generation With Proxy-guided Conditioning\n\nCoin3D is a controlla
 ble and interactive 3D assets generation framework, which integrates 3D-aw
 are controllability from coarse geometry to the 3D generation using a volu
 metric-based 3D adapter. Our interactive modeling workflow facilitates sea
 mless part-aware editing, allows for previewing the edite...\n\n\nWenqi Do
 ng (Zhejiang University); Bangbang Yang, Lin Ma, and Xiao Liu (ByteDance I
 nc.); Liyuan Cui and Hujun Bao (Zhejiang University); Yuewen Ma (ByteDance
  Inc.); and Zhaopeng Cui (Zhejiang University)\n---------------------\nSke
 tchDream: Sketch-based Text-to-3D Generation and Editing\n\nWe present Ske
 tchDream, a novel method that supports text-based NeRF generation from giv
 en hand-drawn sketches and achieves free-view, sketch-based local editing.
  We introduce a sketch-based, multi-view image generation diffusion model 
 to support 3D generation with a coarse-to-fine editing approach ...\n\n\nF
 eng-Lin liu (Institute of Computing Technology, Chinese Academy of Science
 s; University of Chinese Academy of Sciences); Hongbo Fu (City University 
 of Hong Kong); Yu-Kun Lai (Cardiff University); and Lin Gao (Institute of 
 Computing Technology, Chinese Academy of Sciences; University of Chinese A
 cademy of Sciences)\n---------------------\nGenerative 3D Geometry - Inter
 active Discussion\n\nAfter the summary presentations, attendees will parti
 cipate in an interactive discussion. Distributed around the room will be a
  series of poster boards for authors to gather around with the audience. A
 uthors are invited to bring any material related to their paper that could
  instigate further conver...\n\n---------------------\nThemeStation: Gener
 ating Theme-aware 3D Assets From Few Exemplars\n\nThemeStation is an advan
 ced tool for crafting theme-consistent 3D models. From a few exemplars to 
 a universe of 3D assets, our two-stage framework and dual distillation pro
 cess ensure a good blend of unity and diversity. Unleash your creativity w
 ith ThemeStation and step into the realm of effortless...\n\n\nZhenwei Wan
 g (City University of Hong Kong), Tengfei Wang (Shanghai Aritificial Intel
 ligence Laboratory), Gerhard Hancke (City University of Hong Kong), Ziwei 
 Liu (Nanyang Technological University), and Rynson W.H. Lau (City Universi
 ty of Hong Kong)\n\nInterest Area: Research & Education\n\nKeyword: AI, Ge
 ometry, Modeling\n\nRegistration Category: Full Conference, Full Conferenc
 e Supporter, Virtual Access, Exhibitor Full Conference, Monday\n\nSession 
 Chair: Angela Dai (Technical University of Munich)
END:VEVENT
END:VCALENDAR