Hypernetwork approach to generating point clouds

Przemysław Spurek, Sebastian Winczowski, Jacek Tabor, Maciej Zamorski, Maciej Zieba, Tomasz Trzcinski
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:9099-9108, 2020.

Abstract

In this work, we propose a novel method for generating 3D point clouds that leverage properties of hyper networks. Contrary to the existing methods that learn only the representation of a 3D object, our approach simultaneously finds a representation of the object and its 3D surfaces. The main idea of our HyperCloud method is to build a hyper network that returns weights of a particular neural network (target network) trained to map points from a uniform unit ball distribution into a 3D shape. As a consequence, a particular 3D shape can be generated using point-by-point sampling from the assumed prior distribution and transforming sampled points with the target network. Since the hyper network is based on an auto-encoder architecture trained to reconstruct realistic 3D shapes, the target network weights can be considered a parametrisation of the surface of a 3D shape, and not a standard representation of point cloud usually returned by competitive approaches. The proposed architecture allows to find mesh-based representation of 3D objects in a generative manner, while providing point clouds en pair in quality with the state-of-the-art methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v119-spurek20a, title = {Hypernetwork approach to generating point clouds}, author = {Spurek, Przemys{\l}aw and Winczowski, Sebastian and Tabor, Jacek and Zamorski, Maciej and Zieba, Maciej and Trzcinski, Tomasz}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {9099--9108}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/spurek20a/spurek20a.pdf}, url = {https://proceedings.mlr.press/v119/spurek20a.html}, abstract = {In this work, we propose a novel method for generating 3D point clouds that leverage properties of hyper networks. Contrary to the existing methods that learn only the representation of a 3D object, our approach simultaneously finds a representation of the object and its 3D surfaces. The main idea of our HyperCloud method is to build a hyper network that returns weights of a particular neural network (target network) trained to map points from a uniform unit ball distribution into a 3D shape. As a consequence, a particular 3D shape can be generated using point-by-point sampling from the assumed prior distribution and transforming sampled points with the target network. Since the hyper network is based on an auto-encoder architecture trained to reconstruct realistic 3D shapes, the target network weights can be considered a parametrisation of the surface of a 3D shape, and not a standard representation of point cloud usually returned by competitive approaches. The proposed architecture allows to find mesh-based representation of 3D objects in a generative manner, while providing point clouds en pair in quality with the state-of-the-art methods.} }
Endnote
%0 Conference Paper %T Hypernetwork approach to generating point clouds %A Przemysław Spurek %A Sebastian Winczowski %A Jacek Tabor %A Maciej Zamorski %A Maciej Zieba %A Tomasz Trzcinski %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-spurek20a %I PMLR %P 9099--9108 %U https://proceedings.mlr.press/v119/spurek20a.html %V 119 %X In this work, we propose a novel method for generating 3D point clouds that leverage properties of hyper networks. Contrary to the existing methods that learn only the representation of a 3D object, our approach simultaneously finds a representation of the object and its 3D surfaces. The main idea of our HyperCloud method is to build a hyper network that returns weights of a particular neural network (target network) trained to map points from a uniform unit ball distribution into a 3D shape. As a consequence, a particular 3D shape can be generated using point-by-point sampling from the assumed prior distribution and transforming sampled points with the target network. Since the hyper network is based on an auto-encoder architecture trained to reconstruct realistic 3D shapes, the target network weights can be considered a parametrisation of the surface of a 3D shape, and not a standard representation of point cloud usually returned by competitive approaches. The proposed architecture allows to find mesh-based representation of 3D objects in a generative manner, while providing point clouds en pair in quality with the state-of-the-art methods.
APA
Spurek, P., Winczowski, S., Tabor, J., Zamorski, M., Zieba, M. & Trzcinski, T.. (2020). Hypernetwork approach to generating point clouds. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:9099-9108 Available from https://proceedings.mlr.press/v119/spurek20a.html.

Related Material