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

Point cloud analysis is an area of increasing interest due to the developmentof 3D sensors that are able to rapidly measure the depth of scenes accurately.Unfortunately, applying deep learning techniques to perform point cloudanalysis is non-trivial due to the inability of these methods to generalize tounseen rotations. To address this limitation, one usually has to augment thetraining data, which can lead to extra computation and require larger modelcomplexity. This paper proposes a new neural network called the Aligned EdgeConvolutional Neural Network (AECNN) that learns a feature representation ofpoint clouds relative to Local Reference Frames (LRFs) to ensure invariance torotation. In particular, features are learned locally and aligned with respectto the LRF of an automatically computed reference point. The proposed approachis evaluated on point cloud classification and part segmentation tasks. Thispaper illustrates that the proposed technique outperforms a variety of state ofthe art approaches (even those trained on augmented datasets) in terms ofrobustness to rotation without requiring any additional data augmentation.

Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks