IAE: Implicit Autoencoder for Point Cloud Self-supervised Representation Learning

Siming Yan, Zhenpei Yang, Haoxiang Li, Li Guan, Hao Kang, Gang Hua, Qixing Huang

Keywords: point cloud, self-supervised learning, representation learning, autoencoder, implicit function

TL;DR: We propose a simple yet effective non-symmetric autoencoder for point cloud self-supervised learning which leverages implicit function.

Abstract: Autoencoding has been a popular topic across many fields and recently emerged in the 3D domain. However, many 3D representations (e.g., point clouds) are discrete samples of the underlying continuous 3D surface which makes them different from other data modalities. This process inevitably introduces sampling variations on the underlying 3D shapes. In learning 3D representation, a desirable goal is to disregard such sampling variations while focusing on capturing transferable knowledge of the underlying 3D shape. This aim poses a grand challenge to existing representation learning paradigms. For example, the standard autoencoding paradigm forces the encoder to capture such sampling variations as the decoder has to reconstruct the original point cloud. In this paper, we introduce the Implicit Autoencoder (IAE). This simple yet effective method addresses this challenge by replacing the point cloud decoder with an implicit decoder. The implicit decoder can output a continuous representation that is shared among different point cloud samplings of the same model. Reconstructing under the implicit representation can prioritize that the encoder discards sampling variations, introducing appropriate inductive bias to learn more generalizable feature representations. We validate this claim experimentally and show a theoretical analysis under a simple linear autoencoder. Moreover, our implicit decoder offers excellent flexibility in designing suitable implicit representations for different tasks. We demonstrate the usefulness of IAE across various self-supervised learning tasks for both 3D objects and 3D scenes. Experimental results show that IAE consistently outperforms the state-of-the-art in each task.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Unsupervised and Self-supervised learning

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2201.00785/code)