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:20231215T154000
DTEND;TZID=Australia/Melbourne:20231215T155000
UID:siggraphasia_SIGGRAPH Asia 2023_sess159_papers_565@linklings.com
SUMMARY:Anti-Aliased Neural Implicit Surfaces with Encoding Level of Detai
 l
DESCRIPTION:Technical Papers\n\nYiyu Zhuang (Nanjing University); Qi Zhang
  and Ying Feng (Tencent); Hao Zhu and Yao Yao (Nanjing University); Xiaoyu
  Li, Yan-Pei Cao, and Ying Shan (Tencent); and Xun Cao (Nanjing University
 )\n\nWe present LoD-NeuS, an efficient neural representation for high-freq
 uency geometry detail recovery and anti-aliased novel view rendering. Draw
 ing inspiration from voxel-based representations with the level of detail 
 (LoD), we introduce a multi-scale tri-plane-based scene representation tha
 t is capable of capturing the LoD of the signed distance function (SDF) an
 d the space radiance. Our representation aggregates space features from a 
 multi-level convolved featurization within a conical frustum along a ray a
 nd optimizes the LoD feature volume through differentiable rendering. Addi
 tionally, we propose an error-guided sampling strategy to guide the growth
  of the SDF during the optimization. Both qualitative and quantitative eva
 luations demonstrate that our method achieves superior surface reconstruct
 ions and photorealistic view synthesis compared to state-of-the-art approa
 ches.\n\nRegistration Category: Full Access\n\nSession Chair: Fei Hou (Ins
 titute of Software, Chinese Academy of Sciences; University of Chinese Aca
 demy of Sciences)
URL:https://asia.siggraph.org/2023/full-program?id=papers_565&sess=sess159
END:VEVENT
END:VCALENDAR