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:20260817T171536Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241206T144500
DTEND;TZID=Asia/Tokyo:20241206T145600
UID:siggraphasia_SIGGRAPH Asia 2024_sess150_papers_938@linklings.com
SUMMARY:360-degree Human Video Generation with 4D Diffusion Transformer
DESCRIPTION:Ruizhi Shao, Youxin Pang, Zerong Zheng, Jingxiang Sun, and Yeb
 in Liu (Tsinghua University)\n\nWe present a novel approach for generating
  360-degree high-quality, spatio-temporally coherent human videos from a s
 ingle image. Our framework combines the strengths of diffusion transformer
 s for capturing global correlations across viewpoints and time, and CNNs f
 or accurate condition injection. The core is a hierarchical 4D transformer
  architecture that factorizes self-attention across views, time steps, and
  spatial dimensions, enabling efficient modeling of the 4D space. Precise 
 conditioning is achieved by injecting human identity, camera parameters, a
 nd temporal signals into the respective transformers. To train this model,
  we collect a multi-dimensional dataset spanning images, videos, multi-vie
 w data, and limited 4D footage, along with a tailored multi-dimensional tr
 aining strategy. Our approach overcomes the limitations of previous method
 s based on generative adversarial networks or vanilla diffusion models, wh
 ich struggle with complex motions, viewpoint changes, and generalization. 
 Through extensive experiments, we demonstrate our method's ability to synt
 hesize 360-degree realistic, coherent human motion videos, paving the way 
 for advanced multimedia applications in areas such as virtual reality and 
 animation.\n\nRegistration Category: Full Access, Full Access Supporter\n\
 nLanguage Format: English Language\n\nSession Chair: Li-Yi Wei (Adobe Rese
 arch)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_938&sess=sess150
END:VEVENT
END:VCALENDAR