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 325-AB\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221207T170000
DTEND;TZID=Asia/Seoul:20221207T183000
UID:siggraphasia_SIGGRAPH Asia 2022_sess179_papers_363@linklings.com
SUMMARY:CAD2Sketch: Generating Concept Sketches from CAD Sequences
DESCRIPTION:Technical Communications, Technical Papers, TOG\n\nCAD2Sketch:
  Generating Concept Sketches from CAD Sequences\n\nHähnlein, Li, Mitra, Bo
 usseau\n\nConcept sketches are ubiquitous in industrial design, as they al
 low designers to quickly depict imaginary 3D objects.To construct their sk
 etches with accurate perspective, designers rely on longstanding drawing t
 echniques, including the use of auxiliary construction lines to identify m
 idpoints of perspective planes, to align points vertically and horizontall
 y, and to project planar curves from one perspective plane to another. We 
 present a method to synthesize such construction lines from CAD sequences.
  Importantly, our method balances the presence of construction lines with 
 overall clutter, such that the resulting sketch is both well-constructed a
 nd readable, as professional designers are trained to do. In addition to g
 enerating sketches that are visually similar to real ones, we apply our me
 thod to synthesize a large quantity of paired sketches and normal maps, an
 d show that the resulting dataset can be used to train a neural network to
  infer normals from real-world concept sketches.\n\nRegistration Category:
  FULL ACCESS, ON-DEMAND ACCESS\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON, 
 ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_363&sess=sess17
 9
END:VEVENT
END:VCALENDAR