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

Point cloud completion concerns to predict missing part for incomplete 3Dshapes. A common strategy is to generate complete shape according to incompleteinput. However, unordered nature of point clouds will degrade generation ofhigh-quality 3D shapes, as detailed topology and structure of unordered pointsare hard to be captured during the generative process using an extracted latentcode. We address this problem by formulating completion as point clouddeformation process. Specifically, we design a novel neural network, namedPMP-Net++, to mimic behavior of an earth mover. It moves each point ofincomplete input to obtain a complete point cloud, where total distance ofpoint moving paths (PMPs) should be the shortest. Therefore, PMP-Net++ predictsunique PMP for each point according to constraint of point moving distances.The network learns a strict and unique correspondence on point-level, and thusimproves quality of predicted complete shape. Moreover, since moving pointsheavily relies on per-point features learned by network, we further introduce atransformer-enhanced representation learning network, which significantlyimproves completion performance of PMP-Net++. We conduct comprehensiveexperiments in shape completion, and further explore application on point cloudup-sampling, which demonstrate non-trivial improvement of PMP-Net++ overstate-of-the-art point cloud completion/up-sampling methods.

PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Paths