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:20250110T023313Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T130000
DTEND;TZID=Asia/Tokyo:20241206T131400
UID:siggraphasia_SIGGRAPH Asia 2024_sess145_papers_267@linklings.com
SUMMARY:Occupancy-Based Dual Contouring
DESCRIPTION:Technical Papers\n\nJisung Hwang and Minhyuk Sung (Korea Advan
 ced Institute of Science and Technology (KAIST))\n\nWe introduce a dual co
 ntouring method that provides state-of-the-art performance for occupancy f
 unctions while achieving computation times of a few seconds. Our method is
  learning-free and carefully designed to maximize the use of GPU paralleli
 zation. The recent surge of implicit neural representations has led to sig
 nificant attention to occupancy fields, resulting in a wide range of 3D re
 construction and generation methods based on them. However, the outputs of
  such methods have been underestimated due to the bottleneck in converting
  the resulting occupancy function to a mesh. Marching Cubes tends to produ
 ce staircase-like artifacts, and most subsequent works focusing on exploit
 ing signed distance functions as input also yield suboptimal results for o
 ccupancy functions. Based on Manifold Dual Contouring (MDC), we propose Oc
 cupancy-Based Dual Contouring (ODC), which mainly modifies the computation
  of grid edge points (1D points) and grid cell points (3D points) to not u
 se any distance information. We introduce auxiliary 2D points that are use
 d to compute local surface normals along with the 1D points, helping ident
 ify 3D points via the quadric error function. To search the 1D, 2D, and 3D
  points, we develop fast algorithms that are parallelizable across all gri
 d edges, faces, and cells. Our experiments with several 3D neural generati
 ve models and a 3D mesh dataset demonstrate that our method achieves the b
 est fidelity compared to prior works.\n\nRegistration Category: Full Acces
 s, Full Access Supporter\n\nLanguage Format: English Language\n\nSession C
 hair: Hao (Richard) Zhang (Simon Fraser University, Amazon)
URL:https://asia.siggraph.org/2024/program/?id=papers_267&sess=sess145
END:VEVENT
END:VCALENDAR