Go with the Flows: Mixtures of Normalizing Flows for Point Cloud Generation and Reconstruction


METADATA ONLY
Loading...

Date

2021

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Recently Normalizing Flows (NFs) have demonstrated state-of-the-art performance on modeling 3D point clouds while allowing sampling with arbitrary resolution at inference time. However, these flow-based models still have fundamental limitations on complicated geometries. This work generalizes prior work by introducing additional discrete latent variable, i.e. mixture model. This circumvents limitations of prior approaches, leads to more parameter efficient models and reduces the inference runtime. Moreover, in this more general framework each component learns to specialize in a particular subregion of an object in a completely unsupervised fashion yielding promising clustering properties. We further demonstrate that by adding data augmentation, individual mixture components can learn to specialize in a semantically meaningful manner. We evaluate mixtures of NFs on generation, autoencoding and single-view reconstruction based on the ShapeNet dataset.

Publication status

published

Editor

Book title

2021 International Conference on 3D Vision (3DV)

Journal / series

Volume

Pages / Article No.

1249 - 1258

Publisher

IEEE

Event

9th International Conference on 3D Vision (3DV 2021)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Generative models; Normalizing flows; Point clouds; Single view reconstruction

Organisational unit

03514 - Van Gool, Luc (emeritus) / Van Gool, Luc (emeritus) check_circle

Notes

Funding

Related publications and datasets