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 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241204T163000
DTEND;TZID=Asia/Tokyo:20241204T164100
UID:siggraphasia_SIGGRAPH Asia 2024_sess122_papers_630@linklings.com
SUMMARY:InstanceTex: Instance-level Controllable Texture Synthesis for 3D 
 Scenes via Diffusion Priors
DESCRIPTION:Technical Papers\n\nMingxin Yang (Shenzhen Institute of Advanc
 ed Technology, Chinese Academy of Sciences); Jianwei Guo (Institute of Aut
 omation, Chinese Academy Of Sciences); Yuzhi Chen (School of Artificial In
 telligence, University of Chinese Academy of Sciences); Lan Chen (Institut
 e of Automation, Chinese Academy of Sciences); Pu Li (Institute of Automat
 ion, Chinese Academy Of Sciences); Zhanglin Cheng (Shenzhen Institute of A
 dvanced Technology, Chinese Academy of Sciences); Xiaopeng Zhang (Institut
 e of Automation, Chinese Academy Of Sciences); and Hui Huang (Shenzhen Uni
 versity (SZU))\n\nAutomatically generating high-fidelity texture for a com
 plex scene remains an open problem in computer graphics. While pioneering 
 text-to-texture works based on 2D diffusion models have achieved fascinati
 ng results on single objects, they either suffer from style inconsistency 
 and semantic misalignment or require extensive optimization time/memory wh
 en scaling it up to a large scene. To address these challenges, we introdu
 ce InstanceTex, a novel method to synthesize realistic and style-consisten
 t textures for large-scale scenes. At its core, InstanceTex proposes an in
 stance-level controllable texture synthesis approach based on an instance 
 layout representation, which enables precise control over the instances wh
 ile keeping the global style consistency. We also propose a local synchron
 ized multi-view diffusion approach to enhance local texture consistency by
  sharing the latent denoised content among neighboring views in a mini-bat
 ch. Finally, tailored to scene texture mapping, we develop Neural MipTextu
 re inspired by the Mipmaps to reduce the aliasing artifacts. Extensive tex
 turing results on indoor and outdoor scenes show that InstanceTex produces
  high-quality and consistent textures with the superior quality compared t
 o prior texture generation alternatives.\n\nRegistration Category: Full Ac
 cess, Full Access Supporter\n\nLanguage Format: English Language\n\nSessio
 n Chair: Minhyuk Sung (Korea Advanced Institute of Science and Technology 
 (KAIST))
URL:https://asia.siggraph.org/2024/program/?id=papers_630&sess=sess122
END:VEVENT
END:VCALENDAR