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:20260817T171540Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241204T104500
DTEND;TZID=Asia/Tokyo:20241204T115500
UID:siggraphasia_SIGGRAPH Asia 2024_sess114@linklings.com
SUMMARY:Your Wish is my Command: Generate, Edit, Rearrange
DESCRIPTION:Each Paper gives a 10 minute presentation.\n\nLLM-enhanced Sce
 ne Graph Learning for Household Rearrangement\n\nThe household rearrangeme
 nt task involves spotting misplaced objects in a scene and accommodate  th
 em with proper places. It depends both on common-sense knowledge on the ob
 jective side and human user preference on the subjective side. In achievin
 g such task, we propose to mine object functionality ...\n\n\nWenhao Li, Z
 hiyuan Yu, Qijin She, Zhinan Yu, Yuqing Lan, and Chenyang Zhu (National Un
 iversity of Defense Technology (NUDT)); Ruizhen Hu (Shenzhen University (S
 ZU)); and Kai Xu (National University of Defense Technology (NUDT))\n-----
 ----------------\nSGEdit: Bridging LLM with Text2Image Generative Model fo
 r Scene Graph-based Image Editing\n\nScene graphs offer a structured, hier
 archical representation of images, with nodes and edges symbolizing object
 s and the relationships among them. It can serve as a natural interface fo
 r image editing, dramatically improving precision and flexibility. Leverag
 ing this benefit, we introduce a new fram...\n\n\nZhiyuan Zhang (City Univ
 ersity of Hong Kong), DongDong Chen (Microsoft GenAI), and Jing Liao (City
  University of Hong Kong)\n---------------------\nCPoser: An Optimization-
 after-Parsing Approach for Text-to-Pose Generation Using Large Language Mo
 dels.\n\nText-to-pose generation is challenging due to the complexity of n
 atural language and human posture semantics. Utilizing large language mode
 ls (LLMs) for text-to-pose generation is appealing due to their strong cap
 abilities in text understanding and reasoning. However, as LLMs are design
 ed for genera...\n\n\nYumeng Li, Bohong Chen, Zhong Ren, and Yao-Xiang Din
 g (Zhejiang University); Libin Liu (Peking University); and Tianjia Shao a
 nd Kun Zhou (Zhejiang University)\n---------------------\nParSEL: Paramete
 rized Shape Editing with Language\n\nThe ability to edit 3D assets from na
 tural language presents a compelling paradigm to aid in the democratizatio
 n of 3D content creation. However, while natural language is often effecti
 ve at communicating general intent, it is poorly suited for specifying exa
 ct manipulation. To address this gap, we ...\n\n\nAditya Ganeshan, Ryan Hu
 ang, Xianghao Xu, R. Kenny Jones, and Daniel Ritchie (Brown University)\n-
 --------------------\nAutonomous Character-Scene Interaction Synthesis fro
 m Text Instruction\n\nSynthesizing human motions in 3D environments, parti
 cularly those with complex activities such as locomotion, hand-reaching, a
 nd human-object interaction, presents substantial demands for user-defined
  waypoints and stage transitions. These requirements pose challenges for c
 urrent models, leading to ...\n\n\nNan Jiang (Peking University, Beijing I
 nstitute for General Artificial Intelligence); Zimo He (Peking University)
 ; Zi Wang (Beijing University of Posts and Telecommunications); Hongjie Li
  (Peking University); Yixin Chen and Siyuan Huang (Beijing Institute for G
 eneral Artificial Intelligence); and Yixin Zhu (Peking University)\n------
 ---------------\nAnim-Director: A Large Multimodal Model Powered Agent for
  Controllable Animation Video Generation\n\nTraditional animation generati
 on methods depend on training generative models with human-labelled data, 
 entailing a sophisticated multi-stage pipeline that demands substantial hu
 man effort and incurs high training costs. Due to limited prompting plans,
  these methods typically produce brief, informat...\n\n\nYunxin Li, Haoyua
 n Shi, and Baotian Hu (Harbin Institute of Technology); Longyue Wang (Alib
 aba Group); Jiashun Zhu and Jinyi Xu (Jilin University); Zhen Zhao (Tencen
 t AILab); and Min Zhang (Harbin Institute of Technology)\n\nRegistration C
 ategory: Full Access, Full Access Supporter\n\nLanguage Format: English La
 nguage\n\nSession Chair: Kai Wang (Simon Fraser University, ShanghaiTech U
 niversity)
END:VEVENT
END:VCALENDAR