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_563@linklings.com
SUMMARY:Reconstructing editable prismatic CAD from rounded voxel models
DESCRIPTION:Technical Communications, Technical Papers, TOG\n\nReconstruct
 ing editable prismatic CAD from rounded voxel models\n\nLambourne, Willis,
  Jayaraman, Zhang, Sanghi...\n\nReverse Engineering a CAD shape from other
  representations is an important geometric processing step for many downst
 ream applications. In this work, we introduce a novel neural network archi
 tecture to solve this challenging task and approximate a smoothed signed d
 istance function with an editable, constrained, prismatic CAD model. Durin
 g training, our method reconstructs the input geometry in the voxel space 
 by decomposing the shape into a series of 2D profile images and 1D envelop
 e functions.  These can then be recombined in a differentiable way allowin
 g a geometric loss function to be defined. During inference, we obtain the
  CAD data by first searching a database of 2D constrained sketches to find
  curves which approximate the profile images, then extrude them and use Bo
 olean operations to build the final CAD model. Our method approximates the
  target shape more closely than other methods and outputs highly editable 
 constrained parametric sketches which are compatible with existing CAD sof
 tware.\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_563&sess=sess17
 9
END:VEVENT
END:VCALENDAR