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

Generating an interpretable and compact representation of 3D shapes frompoint clouds is an important and challenging problem. This paper presentsCSG-Stump Net, an unsupervised end-to-end network for learning shapes frompoint clouds and discovering the underlying constituent modeling primitives andoperations as well. At the core is a three-level structure called {\emCSG-Stump}, consisting of a complement layer at the bottom, an intersectionlayer in the middle, and a union layer at the top. CSG-Stump is proven to beequivalent to CSG in terms of representation, therefore inheriting theinterpretable, compact and editable nature of CSG while freeing from CSG'scomplex tree structures. Particularly, the CSG-Stump has a simple and regularstructure, allowing neural networks to give outputs of a constantdimensionality, which makes itself deep-learning friendly. Due to thesecharacteristics of CSG-Stump, CSG-Stump Net achieves superior results comparedto previous CSG-based methods and generates much more appealing shapes, asconfirmed by extensive experiments. Project page:https://kimren227.github.io/projects/CSGStump/

CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing