DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM

arXiv:2401.01545v2 Announce Type: replace
Abstract: SLAM systems based on NeRF have demonstrated superior performance in rendering quality and scene reconstruction for static environments compared to traditional dense SLAM. However, they encounter tracking drift and mapping errors in real-world scenarios with dynamic interferences. To address these issues, we introduce DDN-SLAM, the first real-time dense dynamic neural implicit SLAM system integrating semantic features. To address dynamic tracking interferences, we propose a feature point segmentation method that combines semantic features with a mixed …

abstract arxiv cs.cv cs.ro ddn drift dynamic environments errors however mapping nerf performance quality real-time rendering slam systems tracking type world