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

LiDAR Mapping has been a long-standing problem in robotics. Recent progressin neural implicit representation has brought new opportunities to roboticmapping. In this paper, we propose the multi-volume neural feature fields,called NF-Atlas, which bridge the neural feature volumes with pose graphoptimization. By regarding the neural feature volume as pose graph nodes andthe relative pose between volumes as pose graph edges, the entire neuralfeature field becomes both locally rigid and globally elastic. Locally, theneural feature volume employs a sparse feature Octree and a small MLP to encodethe submap SDF with an option of semantics. Learning the map using thisstructure allows for end-to-end solving of maximum a posteriori (MAP) basedprobabilistic mapping. Globally, the map is built volume by volumeindependently, avoiding catastrophic forgetting when mapping incrementally.Furthermore, when a loop closure occurs, with the elastic pose graph basedrepresentation, only updating the origin of neural volumes is required withoutremapping. Finally, these functionalities of NF-Atlas are validated. Thanks tothe sparsity and the optimization based formulation, NF-Atlas shows competitiveperformance in terms of accuracy, efficiency and memory usage on bothsimulation and real-world datasets.

NF-Atlas: Multi-Volume Neural Feature Fields for Large Scale LiDAR Mapping