BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030657Z
LOCATION:Meeting Room S421\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251215T145000
DTEND;TZID=Asia/Hong_Kong:20251215T150000
UID:siggraphasia_SIGGRAPH Asia 2025_sess108_papers_1093@linklings.com
SUMMARY:Simplifying Textured Triangle Meshes in the Wild
DESCRIPTION:Hsueh-Ti Derek Liu and Xiaoting Zhang (Roblox) and Cem Yuksel 
 (University of Utah, Roblox)\n\nThis paper introduces a method for simplif
 ying textured surface triangle meshes in the wild while maintaining high v
 isual quality. While previous methods achieve excellent results on manifol
 d meshes by using the quadric error metric, they struggle to produce high-
 quality outputs for meshes in the wild, which often contain non-manifold e
 lements and multiple connected components. In this work, we begin by outli
 ning the pitfalls of existing mesh simplification techniques and highlight
 ing the discrepancy in their formulations with existing mesh data. In this
  work, we propose a method for simplifying these ``wild'' textured triangl
 e meshes. We formulate mesh simplification as a problem of decimating simp
 licial 2-complexes to handle multiple non-manifold mesh components as a wh
 ole. Building on top of the huge success of quadric error simplification, 
 we iteratively collapse 1-simplices (vertex pairs) with our modified quadr
 ic error that converges to the original quadric error metric for closed ma
 nifold meshes, while greatly improving the results on wild meshes. For tex
 tures, instead of following existing strategies to preserve UVs, we take a
  novel perspective which focuses on computing mesh correspondences through
 out the decimation, regardless of the UV layout. This combination leads to
  a textured mesh simplification system that can operate on arbitrary trian
 gle meshes, leading to high quality results on wild inputs without sacrifi
 cing the excellent performance on clean inputs. Our method guarantees to a
 void common issues in textured mesh simplification, such as texture bleedi
 ng. We extensively evaluate our method on multiple mesh datasets, showing 
 improvements over prior techniques through qualitative and quantitative ev
 aluations, along with user studies.\n\nRegistration Category: Full Access,
  Full Access Supporter\n\nSession Chair: Xiao-Ming Fu (University of Scien
 ce and Technology of China)\n\n
END:VEVENT
END:VCALENDAR