SNI-SLAM is a semantic SLAM system that leverages neural implicit representation to improve dense visual mapping and tracking accuracy while providing semantic mapping of the entire scene. The system introduces hierarchical semantic representation for multi-level comprehension, integrating appearance, geometry, and semantic features through cross-attention for enhanced feature collaboration. By utilizing an internal fusion-based decoder, accurate decoding of semantic, RGB, and TSDF values is achieved from multi-level features. Extensive evaluations on Replica and ScanNet datasets demonstrate superior performance over existing NeRF-based SLAM methods in terms of mapping, tracking accuracy, and semantic segmentation.
Til et annet språk
fra kildeinnhold
arxiv.org
Viktige innsikter hentet fra
by Siting Zhu,G... klokken arxiv.org 03-07-2024
https://arxiv.org/pdf/2311.11016.pdfDypere Spørsmål