3D Point Cloud Completion with Geometric-Aware Adversarial Augmentation

09/21/2021
by   Mengxi Wu, et al.
0

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 in point cloud classification and reconstruction, the role of adversarial samples in3D point cloud completion has seldom been explored. In this work, we show that training with adversarial samples can improve the performance of neural networks on 3D point cloud completion tasks. We propose a novel approach to generate adversarial samples that benefit both the performance of clean and adversarial samples. In contrast to the PGD-k attack, our method generates adversarial samples that keep the geometric features in clean samples and contain few outliers. In particular, we use principal directions to constrain the adversarial perturbations for each input point. The gradient components in the mean direction of principal directions are taken as adversarial perturbations. In addition, we also investigate the effect of using the minimum curvature direction. Besides, we adopt attack strength accumulation and auxiliary Batch Normalization layers method to speed up the training process and alleviate the distribution mismatch between clean and adversarial samples. Experimental results show that training with the adversarial samples crafted by our method effectively enhances the performance of PCN on the ShapeNet dataset.

READ FULL TEXT
research
11/22/2022

PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples

Point cloud completion, as the upstream procedure of 3D recognition and ...
research
05/24/2020

ShapeAdv: Generating Shape-Aware Adversarial 3D Point Clouds

We introduce ShapeAdv, a novel framework to study shape-aware adversaria...
research
03/12/2023

Interpreting Hidden Semantics in the Intermediate Layers of 3D Point Cloud Classification Neural Network

Although 3D point cloud classification neural network models have been w...
research
09/16/2022

PointCAT: Contrastive Adversarial Training for Robust Point Cloud Recognition

Notwithstanding the prominent performance achieved in various applicatio...
research
08/04/2020

AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds

Deep neural networks are vulnerable to adversarial attacks, in which imp...
research
02/25/2020

PointAugment: an Auto-Augmentation Framework for Point Cloud Classification

We present PointAugment, a new auto-augmentation framework that automati...
research
08/17/2022

Imperceptible and Robust Backdoor Attack in 3D Point Cloud

With the thriving of deep learning in processing point cloud data, recen...

Please sign up or login with your details

Forgot password? Click here to reset