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:20240214T070242Z
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:Technical Papers\n\nYuzhe Luo (State Key Laboratory of CAD & C
 G, Zhejiang University; LIGHTSPEED STUDIOS); Xiaogang Jin (State Key Labor
 atory of CAD & CG, Zhejiang University); Zherong Pan and Kui Wu (LIGHTSPEE
 D STUDIOS); Qilong Kou and Xiajun Yang (Tencent Technology (Shenzhen) Co.,
  LTD); and Xifeng Gao (LIGHTSPEED STUDIOS)\n\nOptimizing the memory footpr
 int of 3D models can have a major impact on the user experiences during re
 al-time rendering and streaming visualization, where the major memory over
 head lies in the high-resolution texture data. In this work, we propose a 
 robust and automatic pipeline to content-aware, lossy compression for text
 ure atlas. The design of our solution lies in two observations: 1) mapping
  multiple surface patches to the same texture region is seamlessly compati
 ble with the standard rendering pipeline, requiring no decompression befor
 e any usage; 2) a texture image has background regions and salient structu
 ral features, which can be handled separately to achieve a high compressio
 n rate. Accordingly, our method contains three phases. We first factor out
  redundant salient texture contents by detecting such regions and mapping 
 their corresponding 3D surface patches to a single UV patch via a UV-prese
 rving re-meshing procedure. We then compress redundant background content 
 by clustering triangles into groups by their color. Finally, we create a n
 ew UV atlas with all repetitive texture contents removed, and bake a new t
 exture via differentiable rendering to remove potential inter-patch artifa
 cts. To evaluate the efficacy of our approach, we batch-processed a datase
 t containing 100 models collected online. On average, our method achieves 
 a texture atlas compression ratio of 81.80% with an averaged PSNR and MS-S
 SIM scores of 40.68 and 0.97, a marginal error in visual appearance.\n\nRe
 gistration Category: Full Access, Enhanced Access, Trade Exhibitor, Experi
 ence Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=papers_252&sess=sess209
END:VEVENT
END:VCALENDAR