BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260417T190058Z
LOCATION:West Building\, Rooms 211-214
DTSTART;TZID=America/Los_Angeles:20250811T154500
DTEND;TZID=America/Los_Angeles:20250811T171500
UID:siggraph_SIGGRAPH 2025_sess114@linklings.com
SUMMARY:Tailor Made
DESCRIPTION:Single View Garment Reconstruction Using Diffusion Mapping Via
  Pattern Coordinates\n\nWe introduce a novel method for accurate 3D garmen
 t reconstruction from single-view images, bridging 2D and 3D representatio
 ns. Our mapping model creates connections among image pixels, UV coordinat
 es, and 3D geometry, resulting in realistic garments with intricate detail
 s and enabling downstream ap...\n\n\nRen Li (EPFL), Cong Cao (MBZUAI), Cor
 entin Dumery and Yingxuan You (EPFL), Hao Li (MBZUAI), and Pascal Fua (EPF
 L)\n---------------------\nFast Physics-Based Modeling of Knots and Ties u
 sing Templates\n\nWe propose a physics-based modeling system for knots and
  ties using pipe-like parametric templates, defined by Bézier curves and a
 daptive radii for flexible, intersection-free shapes. Our method maps clot
 h regions from UV space into 3D knot forms via a penetration-free initiali
 zation and supports qu...\n\n\nDewen Guo (Peking University, Style3D Resea
 rch); Zhendong Wang and Zegao Liu (Style3D Research); Sheng Li and Guoping
  Wang (Peking University); Yin Yang (University of Utah); and Huamin Wang 
 (Style3D Research)\n---------------------\nIntersection-Free Garment Retar
 geting\n\nWe introduce an automatic tool to retarget artist-designed garme
 nts on a standard mannequin to possibly non-human avatars with unrealistic
  characteristics, which widely appear in games and animations. We preserve
  the geometrical features in the original design, guarantee intersection-f
 ree, and fit t...\n\n\nZizhou Huang (New York University, Roblox); Chrysti
 ano Araújo and Andrew Kunz (Roblox); Denis Zorin and Daniele Panozzo (New 
 York University); and Victor Zordan (Roblox, Clemson University)\n--------
 -------------\nDress-1-to-3: Single Image to Simulation-Ready 3D Outfit wi
 th Diffusion Prior and Differentiable Physics\n\nWe introduce Dress-1-to-3
  to reconstruct physics-plausible, simulation-ready separated garments fro
 m an in-the-wild image. Starting with the image, our approach combines a p
 re-trained image-to-sewing pattern generation model with a pre-trained mul
 ti-view diffusion model. The sewing pattern is refine...\n\n\nXuan Li, Cha
 ng Yu, Wenxin Du, Ying Jiang, Tianyi Xie, and Yunuo Chen (University of Ca
 lifornia Los Angeles); Yin Yang (University of Utah); and Chenfanfu Jiang 
 (University of California Los Angeles)\n---------------------\nGarmentImag
 e: Raster Encoding of Garment Sewing Patterns with Diverse Topologies\n\nG
 arment sewing patterns often rely on vector formats, which struggle with d
 iscontinuities and unseen topologies. GarmentImage instead encodes geometr
 y, topology, and placement into multi-channel grids, enabling smooth trans
 itions and better generalization. Using simple CNNs, it works well in patt
 ern...\n\n\nYuki Tatsukawa (The University of Tokyo); Anran Qi (INRIA, Uni
 versité Côte d'Azur; The University of Tokyo); and I-Chao Shen and Takeo I
 garashi (The University of Tokyo)\n---------------------\nTailor Made - In
 teractive Discussion\n\nAfter the summary presentations, attendees will pa
 rticipate in an interactive discussion. Outside the room will be a series 
 of poster boards for authors to gather around with the audience. Authors a
 re invited to bring any material related to their paper that could instiga
 te further conversation such...\n\n---------------------\nRags2Riches: Com
 putational Garment Reuse\n\nWe present the first algorithm to automaticall
 y compute sewing patterns for\nupcycling existing garments into new design
 s. Our algorithm takes as input\ntwo garment designs along with their corr
 esponding sewing patterns and\ndetermines how to cut one of them to match 
 the other by following garment\nreus...\n\n\nAnran Qi (INRIA, Université C
 ôte d'Azur); Nico Pietroni (University of Technology Sydney); Maria Korost
 eleva (ETH Zurich, Meshcapade); Olga Sorkine-Hornung (ETH Zurich); and Adr
 ien Bousseau (INRIA, Université Côte d'Azur)\n\nInterest Area: Research & 
 Education\n\nRecording: Livestreamed, Not Livestreamed, Recorded, Not Reco
 rded\n\nRegistration Category: Full Conference, Virtual Access, Monday\n\n
 Session Chair: Emily Whiting (Boston University)
END:VEVENT
END:VCALENDAR