BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250522T212948Z
LOCATION:Mile High 4
DTSTART;TZID=America/Denver:20240729T090000
DTEND;TZID=America/Denver:20240729T103000
UID:siggraph_SIGGRAPH 2024_sess101@linklings.com
SUMMARY:Vector Graphics
DESCRIPTION:Minkowski Penalties: Robust Differentiable Constraint Enforcem
 ent for Vector Graphics\n\nWe introduce a method for laying out complex ar
 rangements of general, nonconvex 2D shapes in the context of vector graphi
 cs, illustration, and diagrams. Beyond simple "no-overlap" conditions, we 
 introduce differentiable penalties for nested containment, tangency, preci
 se padding, etc., which are rob...\n\n\nJiří Minarčík (Independent) and Sa
 m Estep, Wode Ni, and Keenan Crane (Carnegie Mellon University)\n---------
 ------------\nDeep Sketch Vectorization via Implicit Surface Extraction\n\
 nWe propose a sketch vectorization algorithm based on surface extraction f
 rom unsigned distance fields. Our representation is naturally controllable
 , which we demonstrate in an interactive topology refinement interface. We
  achieve far more accurate vectorizations on complex input than previous a
 pproa...\n\n\nChuan Yan (George Mason University); Yong Li (South China Un
 iversity of Technology, George Mason University); Deepali Aneja and Matthe
 w Fisher (Adobe); Edgar Simo-Serra (Waseda University); and Yotam Gingold 
 (George Mason University)\n---------------------\nRobust Containment Queri
 es Over Collections of Rational Parametric Curves via Generalized Winding 
 Numbers\n\nWe extend the theory of generalized winding numbers to unstruct
 ured collections of rational parametric curves with a numerically stable a
 lgorithm, thereby allowing for robust and accurate containment classificat
 ions at arbitrary locations for non-watertight and self-intersecting shape
 s.\n\n\nJacob Spainhour (University of Colorado Boulder), David Gunderman 
 (Indiana University School of Medicine), and Kenneth Weiss (Lawrence Liver
 more National Laboratory)\n---------------------\nText-to-vector Generatio
 n With Neural Path Representation\n\nWe propose a novel pipeline to genera
 te high-quality vector graphics based on text prompts. Utilizing neural pa
 th representation and a two-stage path optimization process, we can incorp
 orate geometric constraints while preserving expressivity in the generated
  SVGs.\n\n\nPeiying Zhang (City University of Hong Kong), Nanxuan Zhao (Ad
 obe Research), and Jing Liao (City University of Hong Kong)\n-------------
 --------\nGPU-accelerated Rendering of Vector Brush Strokes\n\nThis paper 
 introduces GPU-accelerated rendering techniques for digital painting and a
 nimation to bridge the gap between raster and vector stroke representation
 s, including the support for different brush types (vanilla, stamp, airbru
 sh) and an open-source prototype system that can dynamically update...\n\n
 \nShen Ciao, Zhongyue Guan, and Qianxi Liu (Hong Kong University of Scienc
 e and Technology, Guangzhou); Li-Yi Wei (Adobe Research); and Zeyu Wang (H
 ong Kong University of Science and Technology, Guangzhou; Hong Kong Univer
 sity of Science and Technology)\n---------------------\nVector Graphics - 
 Interactive Discussion\n\nAfter the summary presentations, attendees will 
 participate in an interactive discussion. Distributed around the room will
  be a series of poster boards for authors to gather around with the audien
 ce. Authors are invited to bring any material related to their paper that 
 could instigate further conver...\n\n---------------------\nQT-Font: High-
 efficiency Font Synthesis via Quadtree-based Diffusion Models\n\nWe propos
 e a novel sparse glyph representation via quadtree and an efficient font s
 ynthesis method via dual quadtree and discrete diffusion model, QT-Font. Q
 T-Font, compared to existing approaches, can generate high-resolution glyp
 h images with superior quality and more visually pleasing details, me...\n
 \n\nYitian Liu (Peking University, Wangxuan Institute of Computer Technolo
 gy) and Zhouhui Lian (Peking University; Wangxuan Institute of Computer Te
 chnology, Peking University)\n\nInterest Area: Research & Education\n\nKey
 word: Geometry, Modeling\n\nRegistration Category: Full Conference, Full C
 onference Supporter, Virtual Access, Exhibitor Full Conference, Monday\n\n
 Session Chair: Gilbert Bernstein (University of Washington)
END:VEVENT
END:VCALENDAR