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 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:Jisung Hwang and Minhyuk Sung (Korea Advanced Institute of Sci
 ence and Technology (KAIST))\n\nWe introduce a dual contouring method that
  provides state-of-the-art performance for occupancy functions while achie
 ving computation times of a few seconds. Our method is learning-free and c
 arefully designed to maximize the use of GPU parallelization. The recent s
 urge of implicit neural representations has led to significant attention t
 o occupancy fields, resulting in a wide range of 3D reconstruction and gen
 eration methods based on them. However, the outputs of such methods have b
 een underestimated due to the bottleneck in converting the resulting occup
 ancy function to a mesh. Marching Cubes tends to produce staircase-like ar
 tifacts, and most subsequent works focusing on exploiting signed distance 
 functions as input also yield suboptimal results for occupancy functions. 
 Based on Manifold Dual Contouring (MDC), we propose Occupancy-Based Dual C
 ontouring (ODC), which mainly modifies the computation of grid edge points
  (1D points) and grid cell points (3D points) to not use any distance info
 rmation. We introduce auxiliary 2D points that are used to compute local s
 urface normals along with the 1D points, helping identify 3D points via th
 e quadric error function. To search the 1D, 2D, and 3D points, we develop 
 fast algorithms that are parallelizable across all grid edges, faces, and 
 cells. Our experiments with several 3D neural generative models and a 3D m
 esh dataset demonstrate that our method achieves the best fidelity compare
 d to prior works.\n\nRegistration Category: Full Access, Full Access Suppo
 rter\n\nLanguage Format: English Language\n\nSession Chair: Hao (Richard) 
 Zhang (Simon Fraser University, Augmenta)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_267&sess=sess145
END:VEVENT
END:VCALENDAR