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:20250110T023309Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241203T130000
DTEND;TZID=Asia/Tokyo:20241203T131400
UID:siggraphasia_SIGGRAPH Asia 2024_sess104_papers_722@linklings.com
SUMMARY:InfNeRF: Towards Infinite Scale NeRF Rendering with O(log n) Space
  Complexity
DESCRIPTION:Technical Papers\n\nJiabin Liang and Lanqing Zhang (Sea AI Lab
 ), Zhuoran Zhao (National University of Singapore), and Xiangyu Xu (Xi'an 
 Jiaotong University)\n\nThe conventional mesh-based Level of Detail (LoD) 
 technique, exemplified by applications such as Google Earth and many game 
 engines, exhibits the capability to holistically represent a large scene e
 ven the Earth, and achieves rendering with a space complexity of O(log n).
 \nThis constrained data requirement not only enhances rendering efficiency
  but also facilitates dynamic data fetching, thereby enabling a seamless 3
 D navigation experience for users.\nIn this work, we extend this proven Lo
 D technique to Neural Radiance Fields (NeRF) by introducing an octree stru
 cture to represent the scenes in different scales. \nThis innovative appro
 ach provides a mathematically simple and elegant representation with a ren
 dering space complexity of O(log n), aligned with the efficiency of mesh-b
 ased LoD techniques.\nWe also present a novel training strategy that maint
 ains a complexity of O(n). \nThis strategy allows for parallel training wi
 th minimal overhead, ensuring the scalability and efficiency of our propos
 ed method. \nOur contribution is not only in extending the capabilities of
  existing techniques but also in establishing a foundation for scalable an
 d efficient large-scale scene representation using NeRF and octree structu
 res.\n\nRegistration Category: Full Access, Full Access Supporter\n\nLangu
 age Format: English Language\n\nSession Chair: Bernhard Kerbl (Technical U
 niversity of Vienna)
URL:https://asia.siggraph.org/2024/program/?id=papers_722&sess=sess104
END:VEVENT
END:VCALENDAR