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:20260817T171530Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241203T170500
DTEND;TZID=Asia/Tokyo:20241203T171600
UID:siggraphasia_SIGGRAPH Asia 2024_sess110_papers_883@linklings.com
SUMMARY:NeuSmoke: Efficient Smoke Reconstruction and View Synthesis with N
 eural Transportation Fields
DESCRIPTION:Jiaxiong Qiu (TMCC, College of Computer Science, Nankai Univer
 sity; Horizon Robotics); Ruihong Cen (TMCC, College of Computer Science, N
 ankai University); Zhong Li (Apple); Han Yan (Nankai TMCC, College of Comp
 uter Science, Nankai University); and Ming-Ming Cheng and Bo Ren (TMCC, Co
 llege of Computer Science, Nankai University)\n\nNovel view synthesis of s
 moke scenes presents a challenging problem. Previous neural approaches hav
 e suffered from inadequate quality and inefficient training. We introduce 
 NeuSmoke, an efficient framework for dynamic smoke reconstruction using ne
 ural transportation fields, enabling high-quality density reconstruction a
 nd novel-view synthesis from multi-view videos. Our framework consists of 
 two stages. In the first stage, we design a novel neural fluid field repre
 sentation, integrating the transport equation with neural transportation f
 ields. This includes adaptive embedding of multiple time stamps to enhance
  the spatial-temporal consistency of the reconstructed smoke. In the secon
 d stage, we combine novel-view color and depth information, employing conv
 olutional neural networks (CNNs) to refine the smoke reconstruction.  Our 
 model achieves over 10 times faster than previous physics informed approac
 hes. Extensive experiments demonstrate that our method surpasses existing 
 techniques in novel view synthesis and volume density estimation in real-w
 orld and synthetic datasets.\n\nRegistration Category: Full Access, Full A
 ccess Supporter\n\nLanguage Format: English Language\n\nSession Chair: Mic
 hael Wimmer (TU Wien, Technische Universität Wien (TU Wien))\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_883&sess=sess110
END:VEVENT
END:VCALENDAR