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

Motivated by the success of encoding multi-scale contextual information forimage analysis, we propose our PointAtrousGraph (PAG) - a deeppermutation-invariant hierarchical encoder-decoder for efficiently exploitingmulti-scale edge features in point clouds. Our PAG is constructed by severalnovel modules, such as Point Atrous Convolution (PAC), Edge-preserved Pooling(EP) and Edge-preserved Unpooling (EU). Similar with atrous convolution, ourPAC can effectively enlarge receptive fields of filters and thus densely learnmulti-scale point features. Following the idea of non-overlapping max-poolingoperations, we propose our EP to preserve critical edge features duringsubsampling. Correspondingly, our EU modules gradually recover spatialinformation for edge features. In addition, we introduce chained skipsubsampling/upsampling modules that directly propagate edge features to thefinal stage. Particularly, our proposed auxiliary loss functions can furtherimprove our performance. Experimental results show that our PAG outperformprevious state-of-the-art methods on various 3D semantic perceptionapplications.

PointAtrousGraph: Deep Hierarchical Encoder-Decoder with Point Atrous Convolution for Unorganized 3D Points