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:Room 324\, Level 3\, West Wing DTSTART;TZID=Asia/Seoul:20221206T153000 DTEND;TZID=Asia/Seoul:20221206T170000 UID:siggraphasia_SIGGRAPH Asia 2022_sess155_papers_471@linklings.com SUMMARY:Differentiable Point-Based Radiance Fields for Efficient View Synt hesis DESCRIPTION:Technical Communications, Technical Papers\n\nDifferentiable P oint-Based Radiance Fields for Efficient View Synthesis\n\nZhang, Baek, Ru sinkiewicz, Heide\n\nWe propose a differentiable rendering algorithm for e fficient novel view synthesis. By departing from volume-based representati ons in favor of a learned point representation, we improve on existing met hods more than an order of magnitude in memory and runtime, both in traini ng and inference. The method begins with a uniformly-sampled random point cloud and learns per-point position and view-dependent appearance, using a differentiable splat-based renderer to evolve the model to match a set of input images. Our method is up to 300x faster than NeRF in both training and inference, with only a marginal sacrifice in quality, while using less than 10~MB of memory for a static scene. For dynamic scenes, our method t rains two orders of magnitude faster than STNeRF and renders at near inter active rate, while maintaining high image quality and temporal coherence e ven without imposing any temporal-coherency regularizers.\n\nRegistration 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_471&sess=sess15 5 END:VEVENT END:VCALENDAR