Multi-Level Neural Scene Graphs for Dynamic Urban Environments

arXiv:2404.00168v1 Announce Type: new
Abstract: We estimate the radiance field of large-scale dynamic areas from multiple vehicle captures under varying environmental conditions. Previous works in this domain are either restricted to static environments, do not scale to more than a single short video, or struggle to separately represent dynamic object instances. To this end, we present a novel, decomposable radiance field approach for dynamic urban environments. We propose a multi-level neural scene graph representation that scales to thousands of images …

abstract arxiv cs.cv domain dynamic environmental environments graphs instances multiple object scale struggle type urban video