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:20260817T171531Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241204T172800
DTEND;TZID=Asia/Tokyo:20241204T174000
UID:siggraphasia_SIGGRAPH Asia 2024_sess123_papers_1038@linklings.com
SUMMARY:Multi-Resolution Real-Time Deep Pose-Space Deformation
DESCRIPTION:Mianlun Zheng and Jernej Barbic (University of Southern Califo
 rnia)\n\nWe present a hard-real-time multi-resolution mesh shape deformati
 on technique for skeleton-driven soft-body characters. Producing mesh defo
 rmations at multiple levels of detail is very important in many applicatio
 ns in computer graphics. Our work targets applications where the multi-res
 olution shapes must be generated at fast speeds ("hard-real-time", e.g., a
  few milliseconds at most and preferably under 1 millisecond), as commonly
  needed in computer games, virtual reality and Metaverse applications. We 
 assume that the character mesh is driven by a skeleton, and that high-qual
 ity character shapes are available in a set of training poses originating 
 from a high-quality (slow) rig such as volumetric FEM simulation. Our meth
 od combines multi-resolution analysis, mesh partition of unity, and neural
  networks, to learn the pre-skinning shape deformations in an arbitrary ch
 aracter pose. Combined with linear blend skinning, this makes it possible 
 to reconstruct the training shapes, as well as interpolate and extrapolate
  them. Crucially, we simultaneously achieve this at hard real-time rates a
 nd at multiple mesh resolution levels. Our technique makes it possible to 
 trade deformation quality for memory and computation speed, to accommodate
  the strict requirements of modern real-time systems. Furthermore, we prop
 ose memory layout and code improvements to boost computation speeds. Previ
 ous methods for real-time approximations of quality shape deformations did
  not focus on hard real-time, or did not investigate the multi-resolution 
 aspect of the problem. Compared to a ``naive'' approach of separately proc
 essing each hierarchical level of detail, our method offers a substantial 
 memory reduction as well as computational speedups. It also makes it possi
 ble to construct the shape progressively level by level and interrupt the 
 computation at any time, enabling graceful degradation of the deformation 
 detail. We demonstrate our technique on several examples, including a styl
 ized human character, human hands, and an inverse-kinematics-driven quadru
 ped animal.\n\nRegistration Category: Full Access, Full Access Supporter\n
 \nLanguage Format: English Language\n\nSession Chair: Huamin Wang (Style3D
  Research)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_1038&sess=sess123
END:VEVENT
END:VCALENDAR