BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035306Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_322@linklings.com
SUMMARY:Differentiable Rendering of Neural SDFs through Reparameterization
DESCRIPTION:Technical Papers\n\nDifferentiable Rendering of Neural SDFs th
 rough Reparameterization\n\nBangaru, Gharbi, Luan, Li, Sunkavalli...\n\nWe
  present a method to automatically compute correct gradients with respect 
 to geometric scene parameters in neural SDF renderers. Recent physically-b
 ased differentiable rendering techniques for meshes have used edge-samplin
 g to handle discontinuities, particularly at object silhouettes, but SDFs 
 do not have a simple parametric form amenable to sampling. Instead, our ap
 proach builds on area-sampling techniques and develops a continuous warpin
 g function for SDFs to account for these discontinuities. Our method lever
 ages the distance to surface encoded in an SDF and uses quadrature on sphe
 re tracer points to compute this warping function. We further show that th
 is can be done by subsampling the points to make the method tractable for 
 neural SDFs. Our differentiable renderer can be used to optimize neural sh
 apes from multi-view images and produces comparable 3D reconstructions to 
 recent SDF-based inverse rendering methods, without the need for 2D segmen
 tation masks to guide the geometry optimization and no volumetric approxim
 ations to the geometry.\n\nRegistration Category: FULL ACCESS, EXPERIENCE 
 PLUS ACCESS, EXPERIENCE ACCESS, TRADE EXHIBITOR\n\nLanguage: ENGLISH\n\nFo
 rmat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_322&sess=sess15
 3
END:VEVENT
END:VCALENDAR