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:20230103T035307Z LOCATION:Auditorium\, Level 5\, West Wing DTSTART;TZID=Asia/Seoul:20221206T100000 DTEND;TZID=Asia/Seoul:20221206T120000 UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_235@linklings.com SUMMARY:Lightweight Neural Basis Functions for All-Frequency Shading DESCRIPTION:Technical Papers\n\nLightweight Neural Basis Functions for All -Frequency Shading\n\nXu, Zeng, Wu, Wang, Yan\n\nBasis functions provide b oth the abilities for compact representation and the properties for effici ent computation. Therefore, they are pervasively used in rendering to perf orm all-frequency shading. However, common basis functions, including sphe rical harmonics (SH), wavelets, and spherical Gaussians (SG) all have thei r own limitations, such as low-frequency for SH, not rotationally invarian t for wavelets, and no multiple product support for SG. In this paper, we present \empf{neural basis functions}, an implicit and data-driven set of basis functions that circumvents the limitations with all desired properti es. We first introduce a representation neural network that takes any gene ral 2D spherical function (e.g. environment lighting, BRDF, and visibility ) as input and projects it onto the latent space as coefficients of our ne ural basis functions. Then, we design several lightweight neural networks that perform different types of computation, giving our basis functions di fferent computational properties such as double/triple product integrals a nd rotations. We demonstrate the practicality of our neural basis function s by integrating them into all-frequency shading applications, showing tha t our method not only achieves a compression rate of $0.39\%$ and $10\time s$-$40\times$ better performance than wavelets at equal quality, but also renders all-frequency lighting effects in real-time without the aforementi oned limitations from classic basis functions.\n\nRegistration Category: F ULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE ACCESS, TRADE EXHIBITOR\n\n Language: ENGLISH\n\nFormat: IN-PERSON URL:https://sa2022.siggraph.org/en/full-program/?id=papers_235&sess=sess15 3 END:VEVENT END:VCALENDAR