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

The analysis of 3D point clouds has diverse applications in robotics, visionand graphics. Processing them presents specific challenges since they arenaturally sparse, can vary in spatial resolution and are typically unordered.Graph-based networks to abstract features have emerged as a promisingalternative to convolutional neural networks for their analysis, but these canbe computationally heavy as well as memory inefficient. To address theselimitations we introduce a novel Multi-level Graph Convolution Neural (MLGCN)model, which uses Graph Neural Networks (GNN) blocks to extract features from3D point clouds at specific locality levels. Our approach employs precomputedgraph KNNs, where each KNN graph is shared between GCN blocks inside a GNNblock, making it both efficient and effective compared to present models. Wedemonstrate the efficacy of our approach on point cloud based objectclassification and part segmentation tasks on benchmark datasets, showing thatit produces comparable results to those of state-of-the-art models whilerequiring up to a thousand times fewer floating-point operations (FLOPs) andhaving significantly reduced storage requirements. Thus, our MLGCN model couldbe particular relevant to point cloud based 3D shape analysis in industrialapplications when computing resources are scarce.

MLGCN: An Ultra Efficient Graph Convolution Neural Model For 3D Point Cloud Analysis