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:20240214T070245Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T090000
DTEND;TZID=Australia/Melbourne:20231214T091000
UID:siggraphasia_SIGGRAPH Asia 2023_sess148_papers_252@linklings.com
SUMMARY:Texture Atlas Compression Based on Repeated Content Removal
DESCRIPTION:Technical Papers, TOG\n\nYuzhe Luo (State Key Laboratory of CA
 D & CG, Zhejiang University; LIGHTSPEED STUDIOS); Xiaogang Jin (State Key 
 Laboratory of CAD & CG, Zhejiang University); Zherong Pan and Kui Wu (LIGH
 TSPEED STUDIOS); Qilong Kou and Xiajun Yang (Tencent Technology (Shenzhen)
  Co., LTD); and Xifeng Gao (LIGHTSPEED STUDIOS)\n\nOptimizing the memory f
 ootprint of 3D models can have a major impact on the user experiences duri
 ng real-time rendering and streaming visualization, where the major memory
  overhead lies in the high-resolution texture data. In this work, we propo
 se a robust and automatic pipeline to content-aware, lossy compression for
  texture atlas. The design of our solution lies in two observations: 1) ma
 pping multiple surface patches to the same texture region is seamlessly co
 mpatible with the standard rendering pipeline, requiring no decompression 
 before any usage; 2) a texture image has background regions and salient st
 ructural features, which can be handled separately to achieve a high compr
 ession rate. Accordingly, our method contains three phases. We first facto
 r out redundant salient texture contents by detecting such regions and map
 ping their corresponding 3D surface patches to a single UV patch via a UV-
 preserving re-meshing procedure. We then compress redundant background con
 tent by clustering triangles into groups by their color. Finally, we creat
 e a new UV atlas with all repetitive texture contents removed, and bake a 
 new texture via differentiable rendering to remove potential inter-patch a
 rtifacts. To evaluate the efficacy of our approach, we batch-processed a d
 ataset containing 100 models collected online. On average, our method achi
 eves a texture atlas compression 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\n\nSession Chair: Lin Lu (Shandong U
 niversity)
URL:https://asia.siggraph.org/2023/full-program?id=papers_252&sess=sess148
END:VEVENT
END:VCALENDAR