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:20260817T171541Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241205T163000
DTEND;TZID=Asia/Tokyo:20241205T174000
UID:siggraphasia_SIGGRAPH Asia 2024_sess138@linklings.com
SUMMARY:Talking Heads and Moving Faces
DESCRIPTION:Each Paper gives a 10 minute presentation.\n\nVOODOO XP: Expre
 ssive One-Shot Head Reenactment for VR Telepresence\n\nWe introduce VOODOO
  XP: a 3D-aware one-shot head reenactment method that can generate highly 
 expressive facial expressions from any input driver video and a single 2D 
 portrait. Our solution is real-time, view-consistent, and can be instantly
  used without calibration or fine-tuning. We demonstrate ou...\n\n\nPhong 
 Tran (MBZUAI); Egor Zakharov (ETH Zurich); Long-Nhat Ho, Adilbek Karmanov,
  and Ariana Bermudez Venegas (MBZUAI); McLean Goldwhite, Aviral Agarwal, a
 nd Liwen Hu (Pinscreen); Anh Tran (VinAI Research); and Hao Li (MBZUAI, Pi
 nscreen)\n---------------------\nTextToon: Real-Time Text Toonify Head Ava
 tar from Single Video\n\nWe propose TextToon, a method to generate a driva
 ble toonified avatar. Given a short monocular video sequence and a written
  instruction about the avatar style, our model can generate a high-fidelit
 y toonified avatar that can be driven in real-time by another video with a
 rbitrary identities. Existing...\n\n\nLuchuan Song and Lele Chen (Univeris
 ty of Rochester), Celong Liu (Bytedance), Pinxin Liu (University of Roches
 ter), and Chenliang Xu (Univeristy of Rochester)\n---------------------\nP
 ersonaTalk: Bring Attention to Your Persona in Visual Dubbing\n\nFor audio
 -driven visual dubbing, it remains a considerable challenge to uphold and 
 highlight speaker's persona while synthesizing accurate lip synchronizatio
 n. Existing methods fall short of capturing speaker's unique speaking styl
 e or preserving facial details. In this paper, we present PersonaTalk...\n
 \n\nLonghao Zhang, Shuang Liang, Zhipeng Ge, and Tianshu Hu (Bytedance)\n-
 --------------------\nTALK-Act: Enhance Textural-Awareness for 2D Speaking
  Avatar Reenactment with Diffusion Model\n\nRecently, 2D speaking avatars 
 have increasingly participated in everyday scenarios due to the fast devel
 opment of facial animation techniques. However, most existing works neglec
 t the explicit control of human bodies. In this paper, we propose to drive
  not only the faces but also the torso and gestu...\n\n\nJiazhi Guan (Tsin
 ghua University); Quanwei Yang (University of Science and Technology of Ch
 ina); Kaisiyuan Wang, Hang Zhou, Shengyi He, Zhiliang Xu, Haocheng Feng, E
 rrui Ding, and Jingdong Wang (Baidu); Hongtao Xie (University of Science a
 nd Technology of China); Youjian Zhao (Tsinghua University); and Ziwei Liu
  (Nanyang Technological University (NTU))\n---------------------\nFollow-Y
 our-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation\n
 \nWe present Follow-Your-Emoji, a diffusion-based framework for portrait a
 nimation, which animates a reference portrait with target landmark sequenc
 es. The main challenge of portrait animation is to preserve the identity o
 f the reference portrait and transfer the target expression to this portra
 it whi...\n\n\nYue Ma and Hongyu Liu (Hong Kong University of Science and 
 Technology); Hongfa Wang and Heng Pan (Tencent); Yingqing He (Hong Kong Un
 iversity of Science and Technology); Junkun Yuan, Ailing Zeng, and Chengfe
 i Cai (Tencent); Heung-Yeung Shum (Tsinghua University); Wei Liu (Tencent)
 ; and Qifeng Chen (Hong Kong University of Science and Technology)\n------
 ---------------\nFabrig: A Cloth-Simulated Transferable 3D Face Parameteri
 zation\n\nExisting 3D face parameterization methods are limited to human f
 aces and/or require a large amount of manual work to prepare face-specific
  blendshapes. Unfortunately, many of the automated parameterization method
 s do not provide local controls for the different facial regions and metho
 ds that allow ...\n\n\nChangAn Zhu and Chris Joslin (Carleton University)\
 n\nRegistration Category: Full Access, Full Access Supporter\n\nLanguage F
 ormat: English Language\n\nSession Chair: Hongbo Fu (Hong Kong University 
 of Science and Technology)
END:VEVENT
END:VCALENDAR