BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260114T163632Z
LOCATION:Darling Harbour Theatre\, Level 2 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T093000
DTEND;TZID=Australia/Melbourne:20231212T124500
UID:siggraphasia_SIGGRAPH Asia 2023_sess209_papers_252@linklings.com
SUMMARY:Texture Atlas Compression Based on Repeated Content Removal
DESCRIPTION:Yuzhe Luo (State Key Laboratory of CAD & CG, Zhejiang Universi
 ty; LIGHTSPEED STUDIOS); Xiaogang Jin (State Key Laboratory of CAD & CG, Z
 hejiang University); Zherong Pan and Kui Wu (LIGHTSPEED STUDIOS); Qilong K
 ou and Xiajun Yang (Tencent Technology (Shenzhen) Co., LTD); and Xifeng Ga
 o (LIGHTSPEED STUDIOS)\n\nOptimizing the memory footprint of 3D models can
  have a major impact on the user experiences during real-time rendering an
 d streaming visualization, where the major memory overhead lies in the hig
 h-resolution texture data. In this work, we propose a robust and automatic
  pipeline to content-aware, lossy compression for texture atlas. The desig
 n of our solution lies in two observations: 1) mapping multiple surface pa
 tches to the same texture region is seamlessly compatible with the standar
 d rendering pipeline, requiring no decompression before any usage; 2) a te
 xture image has background regions and salient structural features, which 
 can be handled separately to achieve a high compression rate. Accordingly,
  our method contains three phases. We first factor out redundant salient t
 exture contents by detecting such regions and mapping their corresponding 
 3D surface patches to a single UV patch via a UV-preserving re-meshing pro
 cedure. We then compress redundant background content by clustering triang
 les into groups by their color. Finally, we create a new UV atlas with all
  repetitive texture contents removed, and bake a new texture via different
 iable rendering to remove potential inter-patch artifacts. To evaluate the
  efficacy of our approach, we batch-processed a dataset containing 100 mod
 els collected online. On average, our method achieves a texture atlas comp
 ression ratio of 81.80% with an averaged PSNR and MS-SSIM scores of 40.68 
 and 0.97, a marginal error in visual appearance.\n\nRegistration Category:
  Full Access, Enhanced Access, Trade Exhibitor, Experience Hall Exhibitor\
 n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_252&sess=sess209
END:VEVENT
END:VCALENDAR