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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper introduces a fully deep learning approach to monocular SLAM, whichcan perform simultaneous localization using a neural network for learningvisual odometry (L-VO) and dense 3D mapping. Dense 2D flow and a depth imageare generated from monocular images by sub-networks, which are then used by a3D flow associated layer in the L-VO network to generate dense 3D flow. Giventhis 3D flow, the dual-stream L-VO network can then predict the 6DOF relativepose and furthermore reconstruct the vehicle trajectory. In order to learn thecorrelation between motion directions, the Bivariate Gaussian modelling isemployed in the loss function. The L-VO network achieves an overall performanceof 2.68% for average translational error and 0.0143 deg/m for averagerotational error on the KITTI odometry benchmark. Moreover, the learned depthis fully leveraged to generate a dense 3D map. As a result, an entire visualSLAM system, that is, learning monocular odometry combined with dense 3Dmapping, is achieved.

Learning monocular visual odometry with dense 3D mapping from dense 3D flow