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:20260817T171531Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T114300
DTEND;TZID=Asia/Tokyo:20241206T115400
UID:siggraphasia_SIGGRAPH Asia 2024_sess142_papers_138@linklings.com
SUMMARY:NU-NeRF: Neural Reconstruction of Nested Transparent Objects with 
 Uncontrolled Capture Environment
DESCRIPTION:Jia-Mu Sun (Insititute of Computing Technology Chinese Academy
  of Sciences, KIRI Innovations); Tong Wu (Institute of Computing Technolog
 y, Chinese Academy of Sciences; University of Chinese Academy of Sciences)
 ; Ling-Qi Yan (University of California Santa Barbara); and Lin Gao (Insti
 tute of Computing Technology, Chinese Academy of Sciences; University of C
 hinese Academy of Sciences)\n\nThe reconstruction of transparent objects i
 s a challenging problem due to the highly noncontinuous and rapidly changi
 ng surface color caused by refraction. Existing methods rely on special ca
 pture devices, dedicated backgrounds, or ground-truth object masks to prov
 ide more priors and reduce the ambiguity of the problem. However, it is ha
 rd to apply methods with these special requirements to real-life reconstru
 ction tasks, like scenes captured in the wild using mobile devices. Moreov
 er, these methods can only cope with solid and homogeneous materials, grea
 tly limiting the scope of the application. To solve the problems above, we
  propose NU-NeRF to reconstruct nested complex transparent objects requiri
 ng no dedicated capture environment or additional input. NU-NeRF is built 
 upon a neural signed distance field formulation and leverages neural rende
 ring techniques. It consists of two main stages. In Stage I, the surface c
 olor is separated into reflection and refraction. The reflection is decomp
 osed using physically based material and rendering. The refraction is mode
 led using a single MLP given the refraction and view directions, which is 
 a simple yet effective solution of refraction modeling. This step produces
  high-fidelity geometry of the outer surface. In stage II, we use explicit
  ray tracing on the reconstructed outer surface for accurate light transpo
 rt simulation. The surface reconstruction is executed again inside the out
 er geometry to obtain any inner surface geometry. In this process, a novel
  transparent interface formulation is used to cope with different types of
  transparent surfaces. Experiments conducted on synthetic scenes and real 
 captured scenes show that NU-NeRF is capable of producing better reconstru
 ction results than previous methods and achieves accurate nested surface r
 econstruction while requiring no dedicated capture environment.\n\nRegistr
 ation Category: Full Access, Full Access Supporter\n\nLanguage Format: Eng
 lish Language\n\nSession Chair: Maria Larsson (The University of Tokyo)\n\
 n
URL:https://asia.siggraph.org/2024/program/?id=papers_138&sess=sess142
END:VEVENT
END:VCALENDAR