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:20260417T190157Z
LOCATION:West Building\, Rooms 211-214
DTSTART;TZID=America/Los_Angeles:20250811T090000
DTEND;TZID=America/Los_Angeles:20250811T091000
UID:siggraph_SIGGRAPH 2025_sess102_papers_1060@linklings.com
SUMMARY:AssetDropper: Asset Extraction via Diffusion Models with Reward-Dr
 iven Optimization
DESCRIPTION:Lanjiong Li (The Hong Kong University of Science and Technolog
 y (Guangzhou)); Guanhua Zhao (School of Electronic and Computer Engineerin
 g, Peking University); Lingting Zhu (The University of Hong Kong); Zeyu Ca
 i (The Hong Kong University of Science and Technology (Guangzhou)); Lequan
  Yu (The University of Hong Kong); Jian Zhang (School of Electronic and Co
 mputer Engineering, Peking University); and Zeyu Wang (The Hong Kong Unive
 rsity of Science and Technology (Guangzhou), The Hong Kong University of S
 cience and Technology)\n\nAssetDropper is a novel framework for extracting
  standardized assets from reference images, addressing challenges such as 
 occlusion and distortion. Leveraging both synthetic and real-world dataset
 s, along with a reward-driven feedback mechanism, it achieves state-of-the
 -art performance in asset extraction and provides designers with a versati
 le open-world asset palette.\n\nInterest Area: Research & Education\n\nRec
 ording: Livestreamed, Not Livestreamed, Recorded, Not Recorded\n\nRegistra
 tion Category: Full Conference, Virtual Access, Monday\n\nSession Chair: Y
 otam Gingold (George Mason University)\n\n
END:VEVENT
END:VCALENDAR