Adversarial autoencoders for compact representations of 3D point clouds
Maciej Zamorski , M. Zięba , Piotr Klukowski , R Nowak , Karol Kurach , Wojciech Stokowiec , Tomasz Trzciński
AbstractDeep 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.
|Journal series||Computer Vision and Image Understanding, ISSN 1077-3142, e-ISSN 1090-235X|
|Publication size in sheets||0.55|
|Keywords in English||Adversarial AutoencodersPoint CloudsDeep LearningRepresentation LearningNeural NetworksAdversarial Learning|
|ASJC Classification||; ;|
|Score||= 100.0, 26-06-2020, ArticleFromJournal|
|Publication indicators||= 0; = 0; : 2018 = 1.84; : 2018 = 2.645 (2) - 2018=3.077 (5)|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.