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

In this paper, we introduce FMapping, an efficient neural field mappingframework that facilitates the continuous estimation of a colorized point cloudmap in real-time dense RGB SLAM. To achieve this challenging goal withoutdepth, a hurdle is how to improve efficiency and reduce the mapping uncertaintyof the RGB SLAM system. To this end, we first build up a theoretical analysisby decomposing the SLAM system into tracking and mapping parts, and the mappinguncertainty is explicitly defined within the frame of neural representations.Based on the analysis, we then propose an effective factorization scheme forscene representation and introduce a sliding window strategy to reduce theuncertainty for scene reconstruction. Specifically, we leverage the factorizedneural field to decompose uncertainty into a lower-dimensional space, whichenhances robustness to noise and improves training efficiency. We then proposethe sliding window sampler to reduce uncertainty by incorporating coherentgeometric cues from observed frames during map initialization to enhanceconvergence. Our factorized neural mapping approach enjoys some advantages,such as low memory consumption, more efficient computation, and fastconvergence during map initialization. Experiments on two benchmark datasetsshow that our method can update the map of high-fidelity colorized point cloudsaround 2 seconds in real time while requiring no customized CUDA kernels.Additionally, it utilizes x20 fewer parameters than the most concise neuralimplicit mapping of prior methods for SLAM, e.g., iMAP [ 31] and around x1000fewer parameters than the state-of-the-art approach, e.g., NICE-SLAM [ 42]. Formore details, please refer to our project homepage:https://vlis2022.github.io/fmap/.

FMapping: Factorized Efficient Neural Field Mapping for Real-Time Dense RGB SLAM