Benjamin Planche, Xuejian Rong, Ziyan Wu, Srikrishna Karanam, Harald Kosch...
TL;DR本研究提出了一种增量式生成 2D 或 3D 场景的方法,该方法具有全局一致性和局部真实观测结合的特点,能够在先前的全局先验和幻觉的基础上本地生成未观测到的区域,并能够通过自主导航将生成的幻景应用于实际场景,从而解决 SLAM 问题。
Abstract
We present a method to incrementally generate complete 2D or 3D scenes with
the following properties: (a) it is globally consistent at each step according
to a learned scene prior, (b) real observations of a scene can be incorporated
while observing global consistency, (c) unobserved r