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:20230103T035309Z
LOCATION:Room 324\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221207T140000
DTEND;TZID=Asia/Seoul:20221207T153000
UID:siggraphasia_SIGGRAPH Asia 2022_sess159_papers_523@linklings.com
SUMMARY:StyleBin: Stylizing Video by Example in Stereo
DESCRIPTION:Technical Communications, Technical Papers\n\nStyleBin: Styliz
 ing Video by Example in Stereo\n\nKučera, Mould, Sıkora\n\nIn this paper w
 e present StyleBin---an approach to example-based stylization of videos th
 at can produce consistent binocular depiction of stylized content on stere
 oscopic displays. Given the target sequence and a set of stylized keyframe
 s accompanied by information about depth in the scene, we formulate an opt
 imization problem that converts the target video into a pair of stylized s
 equences, in which each frame consists of a set of seamlessly stitched pat
 ches taken from the original stylized keyframe. The aim of the optimizatio
 n process is to align the individual patches so that they respect the sema
 ntics of the given target scene, while at the same time also following the
  prescribed local disparity in the corresponding viewpoints and being cons
 istent in time. In contrast to previous depth-aware style transfer techniq
 ues, our approach is the first that can deliver semantically meaningful st
 ylization and preserve essential visual characteristics of the given artis
 tic media. We demonstrate the practical utility of the proposed method in 
 various stylization use cases.\n\nRegistration Category: FULL ACCESS, ON-D
 EMAND ACCESS\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_523&sess=sess15
 9
END:VEVENT
END:VCALENDAR