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 B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241205T164100
DTEND;TZID=Asia/Tokyo:20241205T165300
UID:siggraphasia_SIGGRAPH Asia 2024_sess138_papers_629@linklings.com
SUMMARY:TextToon: Real-Time Text Toonify Head Avatar from Single Video
DESCRIPTION:Luchuan Song and Lele Chen (Univeristy of Rochester), Celong L
 iu (Bytedance), Pinxin Liu (University of Rochester), and Chenliang Xu (Un
 iveristy of Rochester)\n\nWe propose TextToon, a method to generate a driv
 able toonified avatar. Given a short monocular video sequence and a writte
 n instruction about the avatar style, our model can generate a high-fideli
 ty toonified avatar that can be driven in real-time by another video with 
 arbitrary identities. Existing related works heavily rely on multi-view mo
 deling to recover geometry via texture embeddings, presented in a static m
 anner, leading to control limitations. The multi-view video input also mak
 es it difficult to deploy these models in real-world applications. To addr
 ess these issues, we adopt a conditional embedding Tri-plane to learn real
 istic and stylized facial representations in a Gaussian deformation field.
  Additionally, we expand the stylization capabilities of 3D Gaussian Splat
 ting by introducing an adaptive pixel-translation neural network and lever
 aging patch-aware contrastive learning to achieve high-quality images. To 
 push our work into consumer applications, we develop a real-time system th
 at can operate at 48 FPS on a GPU machine and 15-18 FPS on a mobile machin
 e. Extensive experiments demonstrate the efficacy of our approach in gener
 ating textual avatars over existing methods in terms of quality and real-t
 ime animation. Please refer to our project page for more details: https://
 songluchuan.github.io/TextToon/.\n\nRegistration Category: Full Access, Fu
 ll Access Supporter\n\nLanguage Format: English Language\n\nSession Chair:
  Hongbo Fu (Hong Kong University of Science and Technology)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_629&sess=sess138
END:VEVENT
END:VCALENDAR