BEGIN:VCALENDAR VERSION:2.0 PRODID:Linklings LLC BEGIN:VTIMEZONE TZID:Asia/Seoul X-LIC-LOCATION:Asia/Seoul BEGIN:STANDARD TZOFFSETFROM:+0900 TZOFFSETTO:+0900 TZNAME:KST DTSTART:18871231T000000 DTSTART:19881009T020000 END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20230103T035312Z LOCATION:Room 324\, Level 3\, West Wing DTSTART;TZID=Asia/Seoul:20221208T170000 DTEND;TZID=Asia/Seoul:20221208T183000 UID:siggraphasia_SIGGRAPH Asia 2022_sess167_papers_207@linklings.com SUMMARY:Woven Fabric Capture from a Single Photo DESCRIPTION:Technical Communications, Technical Papers\n\nWoven Fabric Cap ture from a Single Photo\n\nJin, Wang, Hasan, Guo, Marschner...\n\nDigital ly reproducing the appearance of woven fabrics is important in many applic ations of realistic rendering, from interior scenes to virtual characters. However, designing realistic shading models and capturing real fabric sam ples are both challenging tasks. Previous work ranges from applying generi c shading models not meant for fabrics, to data-driven approaches scanning fabrics requiring expensive setups and large data. None of these approach es can turn a single woven fabric sample photograph into a high-accuracy reconstruction enabling compact storage and efficient rendering.\nIn this paper, we propose a woven fabric material model and a parameter estimation approach for it. Our lightweight forward shading model treats yarns as be nt and twisted cylinders, shading these using a microflake-based BRDF mode l. We propose a simple fabric capture configuration, wrapping the fabric s ample on a cylinder of known radius and capturing a single image under kno wn camera and light positions. Our inverse rendering pipeline consists of a neural network to estimate initial fabric parameters and an optimization based on differentiable rendering to refine the results. Our fabric param eter estimation achieves high-quality recovery of measured woven fabric sa mples, which can be used for efficient rendering and further edited.\n\nRe gistration Category: FULL ACCESS, ON-DEMAND ACCESS\n\nLanguage: ENGLISH\n\ nFormat: IN-PERSON, ON-DEMAND URL:https://sa2022.siggraph.org/en/full-program/?id=papers_207&sess=sess16 7 END:VEVENT END:VCALENDAR