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_tog_104@linklings.com SUMMARY:Joint UV Optimization and Texture Baking DESCRIPTION:Technical Papers\n\nJulian Knodt, Zherong Pan, Kui Wu, and Xif eng Gao (LightSpeed Studios)\n\nLevel of detail (LOD) has been widely used in interactive computer graphics. In current industrial 3D modeling pipel ines, artists rely on commercial software to generate highly detailed mode ls with UV maps, and then bake textures for low-poly counterparts. In thes e pipelines, each step is performed separately, leading to unsatisfactory visual appearances for low polygon count models. Moreover, existing textur e baking techniques assume the low-poly mesh has a small geometric differe nce from the high-poly, which is often not true in practice, especially wi th extremely low poly count models. To alleviate the visual discrepancy of the low-poly mesh, we propose to jointly optimize UV mappings during text ure baking, allowing for low-poly models to faithfully replicate the appea rance of the high-poly even with large geometric differences. We formulate the optimization within a differentiable rendering framework, allowing th e automatic adjustment of texture regions to encode appearance information . To compensate for view parallax when two meshes have large geometric dif ferences, we introduce a Spherical Harmonic (SH) parallax mapping, which u ses SH functions to modulate per-texel UV coordinates based on the view di rection. We evaluate the effectiveness and robustness of our approach on a dataset composed of online downloaded models, with varying complexities a nd geometric discrepancies. Our method achieves superior quality over stat e-of-the-art techniques and commercial solutions.\n\nRegistration Category : Full Access, Enhanced Access, Trade Exhibitor, Experience Hall Exhibitor URL:https://asia.siggraph.org/2023/full-program?id=tog_104&sess=sess209 END:VEVENT END:VCALENDAR