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 present D$^2$CSG, a neural model composed of two dual and complementarynetwork branches, with dropouts, for unsupervised learning of compactconstructive solid geometry (CSG) representations of 3D CAD shapes. Our networkis trained to reconstruct a 3D shape by a fixed-order assembly of quadricprimitives, with both branches producing a union of primitive intersections orinverses. A key difference between D$^2$CSG and all prior neural CSG models isits dedicated residual branch to assemble the potentially complex shapecomplement, which is subtracted from an overall shape modeled by the coverbranch. With the shape complements, our network is provably general, while theweight dropout further improves compactness of the CSG tree by removingredundant primitives. We demonstrate both quantitatively and qualitatively thatD$^2$CSG produces compact CSG reconstructions with superior quality and morenatural primitives than all existing alternatives, especially over complex andhigh-genus CAD shapes.

D$^2$CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts