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 method to generate 3D shapes using point clouds. Given apoint-cloud representation of a 3D shape, our method builds a kd-tree tospatially partition the points. This orders them consistently across allshapes, resulting in reasonably good correspondences across all shapes. We thenuse PCA analysis to derive a linear shape basis across the spatiallypartitioned points, and optimize the point ordering by iteratively minimizingthe PCA reconstruction error. Even with the spatial sorting, the point cloudsare inherently noisy and the resulting distribution over the shape coefficientscan be highly multi-modal. We propose to use the expressive power of neuralnetworks to learn a distribution over the shape coefficients in agenerative-adversarial framework. Compared to 3D shape generative modelstrained on voxel-representations, our point-based method is considerably morelight-weight and scalable, with little loss of quality. It also outperformssimpler linear factor models such as Probabilistic PCA, both qualitatively andquantitatively, on a number of categories from the ShapeNet dataset.Furthermore, our method can easily incorporate other point attributes such asnormal and color information, an additional advantage over voxel-basedrepresentations.

Shape Generation using Spatially Partitioned Point Clouds