Implicit Autoencoder for Point Cloud Self-supervised Representation Learning

01/03/2022
by   Siming Yan, et al.
0

Many 3D representations (e.g., point clouds) are discrete samples of the underlying continuous 3D surface. This process inevitably introduces sampling variations on the underlying 3D shapes. In learning 3D representation, the variations should be disregarded while transferable knowledge of the underlying 3D shape should be captured. This becomes a grand challenge in existing representation learning paradigms. This paper studies autoencoding on point clouds. The standard autoencoding paradigm forces the encoder to capture such sampling variations as the decoder has to reconstruct the original point cloud that has sampling variations. We introduce Implicit Autoencoder(IAE), a simple yet effective method that addresses this challenge by replacing the point cloud decoder with an implicit decoder. The implicit decoder outputs a continuous representation that is shared among different point cloud sampling of the same model. Reconstructing under the implicit representation can prioritize that the encoder discards sampling variations, introducing more space to learn useful features. We theoretically justify this claim under a simple linear autoencoder. Moreover, the implicit decoder offers a rich space to design 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/30/2021

NeeDrop: Self-supervised Shape Representation from Sparse Point Clouds using Needle Dropping

There has been recently a growing interest for implicit shape representa...
research
09/13/2022

SeRP: Self-Supervised Representation Learning Using Perturbed Point Clouds

We present SeRP, a framework for Self-Supervised Learning of 3D point cl...
research
08/01/2020

Self-supervised Learning of Point Clouds via Orientation Estimation

Point clouds provide a compact and efficient representation of 3D shapes...
research
05/15/2023

GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-Training

This paper tries to address a fundamental question in point cloud self-s...
research
10/22/2021

AIR-Nets: An Attention-Based Framework for Locally Conditioned Implicit Representations

This paper introduces Attentive Implicit Representation Networks (AIR-Ne...
research
08/05/2018

3D Conceptual Design Using Deep Learning

This article proposes a data-driven methodology to achieve a fast design...
research
03/26/2022

Self-Supervised Point Cloud Representation Learning with Occlusion Auto-Encoder

Learning representations for point clouds is an important task in 3D com...

Please sign up or login with your details

Forgot password? Click here to reset