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:20260817T171534Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241204T163000
DTEND;TZID=Asia/Tokyo:20241204T174000
UID:siggraphasia_SIGGRAPH Asia 2024_sess122@linklings.com
SUMMARY:Text, Texturing, and Stylization
DESCRIPTION:Each Paper gives a 10 minute presentation.\n\nInstanceTex: Ins
 tance-level Controllable Texture Synthesis for 3D Scenes via Diffusion Pri
 ors\n\nAutomatically generating high-fidelity texture for a complex scene 
 remains an open problem in computer graphics. While pioneering text-to-tex
 ture works based on 2D diffusion models have achieved fascinating results 
 on single objects, they either suffer from style inconsistency and semanti
 c misalignm...\n\n\nMingxin Yang (Shenzhen Institute of Advanced Technolog
 y, Chinese Academy of Sciences); Jianwei Guo (Institute of Automation, Chi
 nese Academy Of Sciences); Yuzhi Chen (School of Artificial Intelligence, 
 University of Chinese Academy of Sciences); Lan Chen (Institute of Automat
 ion, Chinese Academy of Sciences); Pu Li (Institute of Automation, Chinese
  Academy Of Sciences); Zhanglin Cheng (Shenzhen Institute of Advanced Tech
 nology, Chinese Academy of Sciences); Xiaopeng Zhang (Institute of Automat
 ion, Chinese Academy Of Sciences); and Hui Huang (Shenzhen University (SZU
 ))\n---------------------\nText-Guided Texturing by Synchronized Multi-Vie
 w Diffusion\n\nThis paper introduces a novel approach to synthesize textur
 e to dress up a given 3D object, given a text prompt. \nBased on the pretr
 ained text-to-image (T2I) diffusion model, existing methods usually employ
  a project-and-inpaint approach, in which a view of the given object is fi
 rst generated and wa...\n\n\nYuxin Liu and Minshan Xie (Chinese University
  of Hong Kong); Hanyuan Liu (City University of Hong Kong); and Tien-Tsin 
 Wong (Monash University, Chinese University of Hong Kong)\n---------------
 ------\nStyleTex: Style Image-Guided Texture Generation for 3D Models\n\nS
 tyle-guided texture generation aims to generate a texture that is harmonio
 us with both the style of the reference image and the geometry of the inpu
 t mesh, given a reference style image and a 3D mesh with its text descript
 ion.  \nAlthough diffusion-based 3D texture generation methods, such as di
 stil...\n\n\nZhiyu Xie, Yuqing Zhang, Xiangjun Tang, Yiqian Wu, and Dehan 
 Chen (State Key Laboratory of CAD&CG, Zhejiang University); Gongsheng Li (
 Zhejiang University); and Xiaogang Jin (State Key Laboratory of CAD&CG, Zh
 ejiang University)\n---------------------\nTEXGen: a Generative Diffusion 
 Model for Mesh Textures\n\nWhile high-quality texture maps are essential f
 or realistic 3D asset rendering, few studies have explored learning direct
 ly in the texture space, especially on large-scale datasets. In this work,
  we depart from the conventional approach of relying on pre-trained 2D dif
 fusion models for test-time opt...\n\n\nXin Yu (University of Hong Kong); 
 Ze Yuan (Beihang University); Yuan-Chen Guo (VAST); Ying-Tian Liu (Tsinghu
 a University); Jianhui Liu (University of Hong Kong); Yangguang Li, Yan-Pe
 i Cao, and Ding Liang (VAST); and Xiaojuan Qi (University of Hong Kong)\n-
 --------------------\nCompositional Neural Textures\n\nTexture plays a vit
 al role in enhancing visual richness in both real photographs and computer
 -generated imagery. However, the process of editing textures often involve
 s laborious and repetitive manual adjustments of textons, which are the re
 curring local patterns that characterize textures. This wor...\n\n\nPeihan
  Tu (University of Maryland, College Park); Li-Yi Wei (Adobe Research); an
 d Matthias Zwicker (University of Maryland, College Park)\n---------------
 ------\nCamera Settings as Tokens: Modeling Photography on Latent Diffusio
 n Models\n\nText-to-image models have revolutionized content creation, ena
 bling users to generate images from natural language prompts. While recent
  advancements in conditioning these models offer more control over the gen
 erated results, photography—a significant artistic domain—remains inadequa
 tely...\n\n\nI-Sheng Fang, Yue-Hua Han, and Jun-Cheng Chen (Academia Sinic
 a)\n\nRegistration Category: Full Access, Full Access Supporter\n\nLanguag
 e Format: English Language\n\nSession Chair: Minhyuk Sung (Korea Advanced 
 Institute of Science and Technology (KAIST))
END:VEVENT
END:VCALENDAR