Skip to Main content Skip to Navigation
Conference papers

Discrete Point Flow Networks for Efficient Point Cloud Generation

Roman Klokov 1 Edmond Boyer 2 Jakob Verbeek 3
1 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
2 MORPHEO - Capture and Analysis of Shapes in Motion
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : Generative models have proven effective at modeling 3D shapes and their statistical variations. In this paper we investigate their application to point clouds, a 3D shape representation widely used in computer vision for which, however, only few generative models have yet been proposed. We introduce a latent variable model that builds on normalizing flows with affine coupling layers to generate 3D point clouds of an arbitrary size given a latent shape representation. To evaluate its benefits for shape modeling we apply this model for generation, autoencoding, and single-view shape reconstruction tasks. We improve over recent GAN-based models in terms of most metrics that assess generation and autoencoding. Compared to recent work based on continuous flows, our model offers a significant speedup in both training and inference times for similar or better performance. For single-view shape reconstruction we also obtain results on par with state-of-the-art voxel, point cloud, and mesh-based methods.
Complete list of metadata

Cited literature [55 references]  Display  Hide  Download
Contributor : Roman Klokov Connect in order to contact the contributor
Submitted on : Monday, July 20, 2020 - 5:06:25 PM
Last modification on : Wednesday, May 4, 2022 - 9:56:05 AM
Long-term archiving on: : Tuesday, December 1, 2020 - 1:55:47 AM


Files produced by the author(s)




Roman Klokov, Edmond Boyer, Jakob Verbeek. Discrete Point Flow Networks for Efficient Point Cloud Generation. ECCV 2020 - 16th European Conference on Computer Vision, Aug 2020, Glasgow, United Kingdom. pp.694-710, ⟨10.1007/978-3-030-58592-1_41⟩. ⟨hal-02903163⟩



Record views


Files downloads