Shrisudhan Govindarajan*1, Daniel Rebain*2, Kwang Moo Yi2, Andrea Tagliasacchi1,3,4 1Simon Fraser University, 2University of British Columbia, 3University of Toronto, 4Google Deepmind * denotes equal contribution Your browser does not support the video tag. Abstract Research on differentiable scene representations is consistently moving towards more efficient, real-time models. Recently, this has led to the popularization of splatting methods, which eschew the traditional ray-based rendering of ...