BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240214T070250Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T162500
DTEND;TZID=Australia/Melbourne:20231215T163500
UID:siggraphasia_SIGGRAPH Asia 2023_sess159_papers_1035@linklings.com
SUMMARY:Neural Gradient Learning and Optimization for Oriented Point Norma
 l Estimation
DESCRIPTION:Technical Papers\n\nQing Li (Tsinghua University), Huifang Fen
 g (Xiamen University), Kanle Shi (Kuaishou Technology), Yi Fang (New York 
 University), Yu-Shen Liu (Tsinghua University), and Zhizhong Han (Wayne St
 ate University)\n\nWe propose Neural Gradient Learning (NGL), a deep learn
 ing approach to learn gradient vectors with consistent orientation from 3D
  point clouds for normal estimation. It has excellent gradient approximati
 on properties for the underlying geometry of the data. We utilize a simple
  neural network to parameterize the objective function to produce gradient
 s at points using a global implicit representation. However, the derived g
 radients usually drift away from the ground-truth oriented normals due to 
 the lack of local detail descriptions. Therefore, we introduce Gradient Ve
 ctor Optimization (GVO) to learn an angular distance field based on local 
 plane geometry to refine the coarse gradient vectors. Finally, we formulat
 e our method with a two-phase pipeline of coarse estimation followed by re
 finement. Moreover, we integrate two weighting functions, i.e., anisotropi
 c kernel and inlier score, into the optimization to improve the robust and
  detail-preserving performance. Our method efficiently conducts global gra
 dient approximation while achieving better accuracy and generalization abi
 lity of local feature description. This leads to a state-of-the-art normal
  estimator that is robust to noise, outliers and point density variations.
  Extensive evaluations show that our method outperforms previous works in 
 both unoriented and oriented normal estimation on widely used benchmarks. 
 The source code and pre-trained models are available at https://github.com
 /LeoQLi/NGLO.\n\nRegistration Category: Full Access\n\nSession Chair: Fei 
 Hou (Institute of Software, Chinese Academy of Sciences; University of Chi
 nese Academy of Sciences)
URL:https://asia.siggraph.org/2023/full-program?id=papers_1035&sess=sess15
 9
END:VEVENT
END:VCALENDAR