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

We propose a data-driven method for recovering miss-ing parts of 3D shapes.Our method is based on a new deep learning architecture consisting of twosub-networks: a global structure inference network and a local geometryrefinement network. The global structure inference network incorporates a longshort-term memorized context fusion module (LSTM-CF) that infers the globalstructure of the shape based on multi-view depth information provided as partof the input. It also includes a 3D fully convolutional (3DFCN) module thatfurther enriches the global structure representation according to volumetricinformation in the input. Under the guidance of the global structure network,the local geometry refinement network takes as input lo-cal 3D patches aroundmissing regions, and progressively produces a high-resolution, complete surfacethrough a volumetric encoder-decoder architecture. Our method jointly trainsthe global structure inference and local geometry refinement networks in anend-to-end manner. We perform qualitative and quantitative evaluations on sixobject categories, demonstrating that our method outperforms existingstate-of-the-art work on shape completion.

High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference