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:20260817T171533Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241204T105600
DTEND;TZID=Asia/Tokyo:20241204T110800
UID:siggraphasia_SIGGRAPH Asia 2024_sess112_papers_237@linklings.com
SUMMARY:Fast and Globally Consistent Normal Orientation based on the Windi
 ng Number Normal Consistency
DESCRIPTION:Siyou Lin (Department of Automation, Tsinghua University); Zuo
 qiang Shi (Yau Mathematical Sciences Center, Tsinghua University; Yanqi La
 ke Beijing Institute of Mathematical Sciences and Applications); and Yebin
  Liu (Department of Automation, Tsinghua University)\n\nEstimating consist
 ently oriented normals for point clouds enables a number of important appl
 ications in computer graphics such as surface reconstruction. While local 
 normal estimation is possible with simple techniques like principal compon
 ent analysis (PCA), orienting these normals to be globally consistent has 
 been a notoriously difficult problem.\nSome recent methods exploit various
  properties of the winding number formula to achieve global consistency wi
 th state-of-the-art performance.\nDespite their exciting progress, these a
 lgorithms either have high space/time complexity, or do not produce accura
 te and consistently oriented normals for imperfect data.\nIn this paper, w
 e propose a novel property from the winding number formula, Winding Number
  Normal Consistency (WNNC), to tackle this problem. The derived property i
 s based on the simple observation that the normals (negative gradients) sa
 mpled from the winding number field should be codirectional to the normals
  used to compute the winding number field. Since the WNNC property itself 
 does not resolve the inside/outside orientation ambiguity, we further prop
 ose to incorporate an objective function from Parametric Gauss Reconstruct
 ion (PGR). We propose to iteratively update normals by alternating between
  WNNC-based normal updates and PGR-based gradient descents, which leads to
  an embarrassingly simple yet effective iterative algorithm that allows fa
 st and high-quality convergence to a globally consistent normal vector fie
 ld.\nFurthermore, our proposed algorithm only involves repeatedly evaluati
 ng the winding number formula and its derivatives, which can be accelerate
 d and parallelized using a treecode-based approximation algorithm due to t
 heir special structures. Exploiting this fact, we implement a GPU-accelera
 ted treecode-based solver. Our GPU (and even CPU) implementation can be si
 gnificantly faster than the recent state-of-the-art methods for normal ori
 entation from raw points. Our code is integrated with the popular PyTorch 
 framework to facilitate further research into winding numbers, and is publ
 icly available at https://jsnln.github.io/wnnc/index.html.\n\nRegistration
  Category: Full Access, Full Access Supporter\n\nLanguage Format: English 
 Language\n\nSession Chair: Michael Wimmer (TU Wien, Technische Universität
  Wien (TU Wien))\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_237&sess=sess112
END:VEVENT
END:VCALENDAR