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

As 3D point clouds become the representation of choice for multiple visionand graphics applications, the ability to synthesize or reconstructhigh-resolution, high-fidelity point clouds becomes crucial. Despite the recentsuccess of deep learning models in discriminative tasks of point clouds,generating point clouds remains challenging. This paper proposes a principledprobabilistic framework to generate 3D point clouds by modeling them as adistribution of distributions. Specifically, we learn a two-level hierarchy ofdistributions where the first level is the distribution of shapes and thesecond level is the distribution of points given a shape. This formulationallows us to both sample shapes and sample an arbitrary number of points from ashape. Our generative model, named PointFlow, learns each level of thedistribution with a continuous normalizing flow. The invertibility ofnormalizing flows enables the computation of the likelihood during training andallows us to train our model in the variational inference framework.Empirically, we demonstrate that PointFlow achieves state-of-the-artperformance in point cloud generation. We additionally show that our model canfaithfully reconstruct point clouds and learn useful representations in anunsupervised manner. The code will be available athttps://github.com/stevenygd/PointFlow.

PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows