Neural Radiance Fields (NeRF)-based Visual Simultaneous Localization and Mapping (SLAM) achieve superior scene geometric modeling and robust camera tracking by leveraging neural representations. Existing methods typically relied on multi-resolution hash encoding with truncated signed distance fields (TSDF) to achieve high frame rates. However, unavoidable hash collisions can lead to artifacts, and multi-view color inconsistencies in indoor scenes can result in shape-radiance ambiguity, adversely affecting geometric quality and tracking accuracy. To address these issues, we propose a novel Multi-scale Hybrid Encoding-based Decoupled SLAM (MHED-SLAM). First, to mitigate the adverse effects of hash collisions and reduce the number of learnable parameters, we innovatively fuse a coarse-scale hash tri-plane with a fine-scale hash grid within a single latent volume. Second, to enable precise geometric reconstruction and camera tracking, we decouple the reconstruction and rendering processes, independently learning a TSDF field for reconstruction and a density field for rendering. Third, we devise a Symmetric Kullback-Leibler (SKL) strategy based on ray termination distributions to align the probability distributions derived from the TSDF and density fields for their synchronous convergence. Extensive experimental evaluations demonstrate that our approach surpasses the state-of-the-art (SOTA) methods by utilizing a faster frame rate of 20 Hz and fewer parameters, while achieving higher tracking and reconstruction accuracy.

Interpretation of Chinese address information, which refers to translating the non-specification Chinese address into the concrete administration divisions, is a critical prerequisite in Internet geography semantic comprehension and Chinese address navigation. In this paper, We proposed Multi-factor(MF) Inference technology to solve the problem of vague address semantics. Firstly, we define the location and match factors of each geographical element in a series of address, which need to be included in a various address relationship. Secondly, the reliability of each possible address string is inferred. Finally, the highest reliability is choosed. Expriments show that our method outperforms current state-of-the-art methds.