3D Point Cloud Completion with Geometric-Aware Adversarial Augmentation

Mengxi Wu, Hao Huang, Yi Fang

Research output: Chapter in Book/Report/Conference proceedingConference contribution


With the popularity of 3D sensors in self-driving and other robotics applications, extensive research has focused on designing novel neural network architectures for accurate 3D point cloud completion. However, unlike point cloud classification and reconstruction, the role of adversarial samples in 3D point cloud completion has seldom been explored. In this work, we demonstrate that adversarial samples can benefit neural networks on 3D point cloud completion tasks. We propose a novel approach to craft adversarial samples that improve the performance of models on both clean and adversarial inputs. In contrast to the Projected Gradient Descent (PGD) attack, our method generates adversarial samples that keep the geometric features in clean samples and contain few outliers. In particular, we use minimum absolute curvature directions to constrain the adversarial perturbations for each input point. The gradient components in the minimum absolute curvature directions are taken as adversarial perturbations. In addition, we adopt attack strength accumulation and auxiliary Batch Normalization layers to speed up the training process and alleviate the distribution mismatch between clean and adversarial samples. Experimental results demonstrate that training with the adversarial samples crafted by our method under the geometric-aware constraint effectively enhances the performance of the Point Completion Network (PCN) on the ShapeNet dataset.

Original languageEnglish (US)
Title of host publication2022 26th International Conference on Pattern Recognition, ICPR 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages7
ISBN (Electronic)9781665490627
StatePublished - 2022
Event26th International Conference on Pattern Recognition, ICPR 2022 - Montreal, Canada
Duration: Aug 21 2022Aug 25 2022

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651


Conference26th International Conference on Pattern Recognition, ICPR 2022


  • 3D Point Cloud Completion
  • Adversarial Machine Learning

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition


Dive into the research topics of '3D Point Cloud Completion with Geometric-Aware Adversarial Augmentation'. Together they form a unique fingerprint.

Cite this