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

Camera localization in 3D LiDAR maps has gained increasing attention due toits promising ability to handle complex scenarios, surpassing the limitationsof visual-only localization methods. However, existing methods mostly focus onaddressing the cross-modal gaps, estimating camera poses frame by frame withoutconsidering the relationship between adjacent frames, which makes the posetracking unstable. To alleviate this, we propose to couple the 2D-3Dcorrespondences between adjacent frames using the 2D-2D feature matching,establishing the multi-view geometrical constraints for simultaneouslyestimating multiple camera poses. Specifically, we propose a new 2D-3D posetracking framework, which consists: a front-end hybrid flow estimation networkfor consecutive frames and a back-end pose optimization module. We furtherdesign a cross-modal consistency-based loss to incorporate the multi-viewconstraints during the training and inference process. We evaluate our proposedframework on the KITTI and Argoverse datasets. Experimental results demonstrateits superior performance compared to existing frame-by-frame 2D-3D posetracking methods and state-of-the-art vision-only pose tracking algorithms.More online pose tracking videos are available at\url{https://youtu.be/yfBRdg7gw5M}

2D-3D Pose Tracking with Multi-View Constraints