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

Understanding dynamic 3D environment is crucial for robotic agents and manyother applications. We propose a novel neural network architecture called$MeteorNet$ for learning representations for dynamic 3D point cloud sequences.Different from previous work that adopts a grid-based representation andapplies 3D or 4D convolutions, our network directly processes point clouds. Wepropose two ways to construct spatiotemporal neighborhoods for each point inthe point cloud sequence. Information from these neighborhoods is aggregated tolearn features per point. We benchmark our network on a variety of 3Drecognition tasks including action recognition, semantic segmentation and sceneflow estimation. MeteorNet shows stronger performance than previous grid-basedmethods while achieving state-of-the-art performance on Synthia. MeteorNet alsooutperforms previous baseline methods that are able to process at most twoconsecutive point clouds. To the best of our knowledge, this is the first workon deep learning for dynamic raw point cloud sequences.

MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences