Adversarial autoencoders for compact representations of 3D point clouds

Maciej Zamorski , M. Zięba , Piotr Klukowski , R Nowak , Karol Kurach , Wojciech Stokowiec , Tomasz Trzciński


Deep generative architectures provide a way to model not only images but also complex, 3-dimensional objects, such as point clouds. In this work, we present a novel method to obtain meaningful representations of 3D shapes that can be used for challenging tasks, including 3D points generation, reconstruction, compression, and clustering. Contrary to existing methods for 3D point cloud generation that train separate decoupled models for representation learning and generation, our approach is the first end-to-end solution that allows to simultaneously learn a latent space of representation and generate 3D shape out of it. Moreover, our model is capable of learning meaningful compact binary descriptors with adversarial training conducted on a latent space. To achieve this goal, we extend a deep Adversarial Autoencoder model (AAE) to accept 3D input and create 3D output. Thanks to our end-to-end training regime, the resulting method called 3D Adversarial Autoencoder (3dAAE) obtains either binary or continuous latent space that covers a much broader portion of training data distribution. Finally, our quantitative evaluation shows that 3dAAE provides state-of-the-art results for 3D points clustering and 3D object retrieval.
Author Maciej Zamorski
Maciej Zamorski,,
, M. Zięba
M. Zięba,,
, Piotr Klukowski (FACME / IMDF)
Piotr Klukowski,,
- Institute of Machine Design Fundamentals
, R Nowak
R Nowak,,
, Karol Kurach
Karol Kurach,,
, Wojciech Stokowiec (FMIS) - Polsko-Japońska Akademia Technik Informacyjnych, Tooploox, Wrocłąw
Wojciech Stokowiec,,
- Faculty of Mathematics and Information Science
, Tomasz Trzciński (FEIT / IN)
Tomasz Trzciński,,
- The Institute of Computer Science
Journal seriesComputer Vision and Image Understanding, ISSN 1077-3142, e-ISSN 1090-235X
Issue year2020
Publication size in sheets0.55
Article number102921
Keywords in EnglishAdversarial AutoencodersPoint CloudsDeep LearningRepresentation LearningNeural NetworksAdversarial Learning
ASJC Classification1707 Computer Vision and Pattern Recognition; 1711 Signal Processing; 1712 Software
Languageen angielski
Score (nominal)100
Score sourcejournalList
ScoreMinisterial score = 100.0, 26-06-2020, ArticleFromJournal
Publication indicators WoS Citations = 0; Scopus Citations = 0; Scopus SNIP (Source Normalised Impact per Paper): 2018 = 1.84; WoS Impact Factor: 2018 = 2.645 (2) - 2018=3.077 (5)
Citation count*
Share Share

Get link to the record

* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Are you sure?