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

Most scanning LiDAR sensors generate a sequence of point clouds in real-time.While conventional 3D object detectors use a set of unordered LiDAR pointsacquired over a fixed time interval, recent studies have revealed thatsubstantial performance improvement can be achieved by exploiting thespatio-temporal context present in a sequence of LiDAR point sets. In thispaper, we propose a novel 3D object detection architecture, which can encodeLiDAR point cloud sequences acquired by multiple successive scans. The encodingprocess of the point cloud sequence is performed on two different time scales.We first design a short-term motion-aware voxel encoding that captures theshort-term temporal changes of point clouds driven by the motion of objects ineach voxel. We also propose long-term motion-guided bird's eye view (BEV)feature enhancement that adaptively aligns and aggregates the BEV feature mapsobtained by the short-term voxel encoding by utilizing the dynamic motioncontext inferred from the sequence of the feature maps. The experimentsconducted on the public nuScenes benchmark demonstrate that the proposed 3Dobject detector offers significant improvements in performance compared to thebaseline methods and that it sets a state-of-the-art performance for certain 3Dobject detection categories. Code is available athttps://github.com/HYjhkoh/MGTANet.git

MGTANet: Encoding Sequential LiDAR Points Using Long Short-Term Motion-Guided Temporal Attention for 3D Object Detection