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

Collaborative 3D object detection exploits information exchange amongmultiple agents to enhance accuracy of object detection in presence of sensorimpairments such as occlusion. However, in practice, pose estimation errors dueto imperfect localization would cause spatial message misalignment andsignificantly reduce the performance of collaboration. To alleviate adverseimpacts of pose errors, we propose CoAlign, a novel hybrid collaborationframework that is robust to unknown pose errors. The proposed solution relieson a novel agent-object pose graph modeling to enhance pose consistency amongcollaborating agents. Furthermore, we adopt a multi-scale data fusion strategyto aggregate intermediate features at multiple spatial resolutions. Comparingwith previous works, which require ground-truth pose for training supervision,our proposed CoAlign is more practical since it doesn't require anyground-truth pose supervision in the training and makes no specific assumptionson pose errors. Extensive evaluation of the proposed method is carried out onmultiple datasets, certifying that CoAlign significantly reduce relativelocalization error and achieving the state of art detection performance whenpose errors exist. Code are made available for the use of the researchcommunity at https://github.com/yifanlu0227/CoAlign.

Robust Collaborative 3D Object Detection in Presence of Pose Errors