TivNe-SLAM: Dynamic Tracking and Mapping via Time-Varying Neural Radiance Fields

arXiv:2310.18917v3 Announce Type: replace
Abstract: Previous attempts to integrate Neural Radiance Fields (NeRF) into Simultaneous Localization and Mapping (SLAM) framework either rely on the assumption of static scenes or treat dynamic objects as outliers. However, most of real-world scenarios is dynamic. In this paper, we propose a time-varying representation to track and reconstruct the dynamic scenes. Firstly, two processes, tracking process and mapping process, are simultaneously maintained in our system. For tracking process, \red{the entire input images are} uniformly sampled, …

abstract arxiv cs.cv dynamic fields framework however localization mapping nerf neural radiance fields objects outliers paper representation slam tracking type via world