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:20260805T205601Z
LOCATION:Room 408 B
DTSTART;TZID=America/Los_Angeles:20260723T162500
DTEND;TZID=America/Los_Angeles:20260723T163500
UID:siggraph_SIGGRAPH 2026_sess138_paperstog_112@linklings.com
SUMMARY:RaDe-GS: Rasterizing Depth in Gaussian Splatting
DESCRIPTION:Baowen Zhang and Chuan Fang (Hong Kong University of Science a
 nd Technology), Rakesh Shrestha (Simon Fraser University), Yixun Liang (Ho
 ng Kong University of Science and Technology), xiaoxiao Long (Nanjing Univ
 ersity), Ping Tan (Hong Kong University of Science and Technology), and Ba
 owen Zhang\n\nGaussian Splatting enables high-quality, real-time novel-vie
 w synthesis, but extracting detailed 3D geometry remains challenging. We i
 ntroduce a rasterized approach to render the depth and normal maps for gen
 eral 3D Gaussian primitives. Our method significantly enhances shape recon
 struction accuracy while maintaining the computational efficiency of Gauss
 ian Splatting.\n\nInterest Area: Research & Education\n\nKeyword: Generati
 ve AI, Geometry, Modeling, Rendering\n\nRegistration Category: Full Confer
 ence Supporter, Full Conference\n\nSession Chair: Hongzhi Wu (Zhejiang Uni
 versity; State Key Laboratory of CAD&CG, Zhejiang University)\n\n
END:VEVENT
END:VCALENDAR