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 DDN-SLAM, a real-time dense neural implicit semantic SLAM systemdesigned for dynamic scenes. While existing neural implicit SLAM systemsperform well in static scenes, they often encounter challenges in real-worldenvironments with dynamic interferences, leading to ineffective tracking andmapping. DDN-SLAM utilizes the priors provided by the deep semantic system,combined with conditional probability fields, for segmentation.By constructingdepth-guided static masks and employing joint multi-resolution hashingencoding, we ensure fast hole filling and high-quality mapping while mitigatingthe effects of dynamic information interference. To enhance trackingrobustness, we utilize sparse feature points validated with optical flow andkeyframes, enabling loop closure detection and global bundle optimization.Furthermore, DDN-SLAM supports monocular, stereo, and RGB-D inputs, operatingrobustly at a frequency of 20-30Hz. Extensive experiments on 6 virtual/realdatasets demonstrate that our method outperforms state-of-the-art approaches inboth dynamic and static scenes.

DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM with Joint Semantic Encoding