BEGIN:VCALENDAR VERSION:2.0 PRODID:Linklings LLC BEGIN:VTIMEZONE TZID:Asia/Tokyo X-LIC-LOCATION:Asia/Tokyo BEGIN:STANDARD TZOFFSETFROM:+0900 TZOFFSETTO:+0900 TZNAME:JST DTSTART:18871231T000000 END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20250110T023312Z LOCATION:Hall B7 (1)\, B Block\, Level 7 DTSTART;TZID=Asia/Tokyo:20241205T172800 DTEND;TZID=Asia/Tokyo:20241205T174000 UID:siggraphasia_SIGGRAPH Asia 2024_sess138_papers_1197@linklings.com SUMMARY:Fabrig: A Cloth-Simulated Transferable 3D Face Parameterization DESCRIPTION:Technical Papers\n\nChangAn Zhu and Chris Joslin (Carleton Uni versity)\n\nExisting 3D face parameterization methods are limited to human faces and/or require a large amount of manual work to prepare face-specif ic blendshapes. Unfortunately, many of the automated parameterization meth ods do not provide local controls for the different facial regions and met hods that allow the integration of physics-based simulations also suffer f rom limited character compatibility and editability. We propose a human fa ce anatomy-inspired 3D face parameterization method called Fabrig, which i s quick to set up, transferable among various characters, easily editable, and compatible with physics-based simulations. Instead of using conventio nal volume-centric simulation for the face anatomy, our method innovativel y uses cloth simulation for lighter computation. The parameterized faces s upport physics-based effects like collision and show skin details such as dynamic wrinkles.\nFrom our objective evaluation, we found that our method can parameterize the faces of various characters, ranging from realistic humans to non-humans, without any labor-demanding preparation work. The pa rameterized faces can be edited at the anatomical level while remaining in tuitive to artists. Our evaluation results confirm that this new parameter ization can accurately and naturally recreate the facial poses of a charac ter or facial actions performed by a motion capture subject.\n\nRegistrati on Category: Full Access, Full Access Supporter\n\nLanguage Format: Englis h Language\n\nSession Chair: Hongbo Fu (Hong Kong University of Science an d Technology) URL:https://asia.siggraph.org/2024/program/?id=papers_1197&sess=sess138 END:VEVENT END:VCALENDAR