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:20230103T035307Z
LOCATION:Room 324\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T153000
DTEND;TZID=Asia/Seoul:20221206T170000
UID:siggraphasia_SIGGRAPH Asia 2022_sess155_papers_560@linklings.com
SUMMARY:Depth of Field Aware Differentiable Rendering
DESCRIPTION:Technical Communications, Technical Papers\n\nDepth of Field A
 ware Differentiable Rendering\n\nPidhorskyi, Bagautdinov, Ma, Saragih, Sch
 wartz...\n\nCameras with a finite aperture diameter exhibit defocus for sc
 ene elements that are not at the focus distance and have only a limited de
 pth of field within which objects appear acceptably sharp. In this work, w
 e address the problem of applying inverse rendering techniques to input da
 ta that exhibits such defocus blurring. We present differentiable depth-of
 -field rendering techniques that are applicable to both rasterization-base
 d methods using mesh representations, as well as ray-marching-based method
 s using volumetric radiance fields. Our approach learns significantly shar
 per scene reconstructions on data containing blur due to depth of field an
 d recovers aperture and focus distance parameters that result in plausible
  forward-rendered images. We show applications to macro photography, where
  typical lens configurations result in a very narrow depth of field, and t
 o multi-camera video capture, where maintaining sharp focus across a large
  capture volume for a moving subject is difficult.\n\nRegistration Categor
 y: FULL ACCESS, ON-DEMAND ACCESS\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON
 , ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_560&sess=sess15
 5
END:VEVENT
END:VCALENDAR