English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We propose SNI-SLAM, a semantic SLAM system utilizing neural implicitrepresentation, that simultaneously performs accurate semantic mapping,high-quality surface reconstruction, and robust camera tracking. In thissystem, we introduce hierarchical semantic representation to allow multi-levelsemantic comprehension for top-down structured semantic mapping of the scene.In addition, to fully utilize the correlation between multiple attributes ofthe environment, we integrate appearance, geometry and semantic featuresthrough cross-attention for feature collaboration. This strategy enables a moremultifaceted understanding of the environment, thereby allowing SNI-SLAM toremain robust even when single attribute is defective. Then, we design aninternal fusion-based decoder to obtain semantic, RGB, Truncated SignedDistance Field (TSDF) values from multi-level features for accurate decoding.Furthermore, we propose a feature loss to update the scene representation atthe feature level. Compared with low-level losses such as RGB loss and depthloss, our feature loss is capable of guiding the network optimization on ahigher-level. Our SNI-SLAM method demonstrates superior performance over allrecent NeRF-based SLAM methods in terms of mapping and tracking accuracy onReplica and ScanNet datasets, while also showing excellent capabilities inaccurate semantic segmentation and real-time semantic mapping.

SNI-SLAM: Semantic Neural Implicit SLAM