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:20240214T070241Z 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_626@linklings.com SUMMARY:SAME: Skeleton-Agnostic Motion Embedding for Character Animation DESCRIPTION:Technical Papers\n\nSunmin Lee, Taeho Kang, and Jungnam Park ( Seoul National University); Jehee Lee (NC Research, Seoul National Univers ity); and Jungdam Won (Seoul National University)\n\nLearning deep neural networks on human motion data has become common in computer graphics resea rch, but the heterogeneity of available datasets poses challenges for trai ning large-scale networks. \nThis paper presents a framework that allows u s to solve various animation tasks in a skeleton-agnostic manner. The core of our framework is to learn an embedding space to disentangle skeleton-r elated information from input motion while preserving semantics, which we call Skeleton-Agnostic Motion Embedding (SAME). To efficiently learn the e mbedding space, we develop a novel autoencoder with graph convolution netw orks, and we provide new formulations of various animation tasks operating in the SAME space. We showcase various examples, including retargeting, r econstruction, and interactive character control, and conduct an ablation study to validate design choices made during development.\n\nRegistration Category: Full Access, Enhanced Access, Trade Exhibitor, Experience Hall E xhibitor URL:https://asia.siggraph.org/2023/full-program?id=papers_626&sess=sess209 END:VEVENT END:VCALENDAR