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:20231215T155000
DTEND;TZID=Australia/Melbourne:20231215T160500
UID:siggraphasia_SIGGRAPH Asia 2023_sess159_papers_142@linklings.com
SUMMARY:Neural-Singular-Hessian: Implicit Neural Representation of Unorien
 ted Point Clouds by Enforcing Singular Hessian
DESCRIPTION:Technical Papers\n\nZixiong Wang, Yunxiao Zhang, and Rui Xu (S
 handong University); Fan Zhang (Shandong Technology and Business Universit
 y); Peng-Shuai Wang (Peking University); Shuangmin Chen (Qingdao Universit
 y of Science and Technology); Shiqing Xin (Shandong University); Wenping W
 ang (Texas A&M University); and Changhe Tu (Shandong University)\n\nNeural
  implicit representation is a promising approach for reconstructing surfac
 es from point clouds. Existing methods combine various regularization term
 s to enforce the learned neural function to possess the properties of a SD
 F, such as the Eikonal term and Laplacian energy term. However, when the i
 nput is an unoriented point cloud of poor quality, inferring the actual to
 pology and geometry of the underlying surface becomes challenging. In acco
 rdance with Differential Geometry, the Hessian of the SDF is singular for 
 any point located within the differential thin-shell space surrounding the
  surface. Based on this fact, our approach enforces the Hessian of the SDF
  to have a zero determinant for points in close proximity to the input poi
 nt cloud, rather than using a smoothness term. This technique quickly elim
 inates critical points of the SDF near the surface, producing a coarse but
  faithful shape. By annealing the weight of the critical-point elimination
  term, our approach can ultimately produce a high-fidelity reconstruction 
 result. The validity of this approach can be established through Morse the
 ory. Our approach has demonstrated better expressiveness in recovering det
 ails from unoriented point clouds while effectively suppressing ghost geom
 etry, as evidenced by extensive experimental results in comparison to exis
 ting fitting-based methods.\n\nRegistration Category: Full Access\n\nSessi
 on Chair: Fei Hou (Institute of Software, Chinese Academy of Sciences; Uni
 versity of Chinese Academy of Sciences)
URL:https://asia.siggraph.org/2023/full-program?id=papers_142&sess=sess159
END:VEVENT
END:VCALENDAR