Risk-optimized Outlier Removal for Robust Point Cloud Classification

by   Xinke Li, et al.

The popularity of point cloud deep models for safety-critical purposes has increased, but the reliability and security of these models can be compromised by intentional or naturally occurring point cloud noise. To combat this issue, we present a novel point cloud outlier removal method called PointCVaR, which empowers standard-trained models to eliminate additional outliers and restore the data. Our approach begins by conducting attribution analysis to determine the influence of each point on the model output, which we refer to as point risk. We then optimize the process of filtering high-risk points using Conditional Value at Risk (CVaR) as the objective. The rationale for this approach is based on the observation that noise points in point clouds tend to cluster in the tail of the risk distribution, with a low frequency but a high level of risk, resulting in significant interference with classification results. Despite requiring no additional training effort, our method produces exceptional results in various removal-and-classification experiments for noisy point clouds, which are corrupted by random noise, adversarial noise, and backdoor trigger noise. Impressively, it achieves 87 against the backdoor attack by removing triggers. Overall, the proposed PointCVaR effectively eliminates noise points and enhances point cloud classification, making it a promising plug-in module for various models in different scenarios.


page 1

page 2

page 3

page 4


POINTCLEANNET: Learning to Denoise and Remove Outliers from Dense Point Clouds

Point clouds obtained with 3D scanners or by image-based reconstruction ...

Nudge Attacks on Point-Cloud DNNs

The wide adaption of 3D point-cloud data in safety-critical applications...

Critical Points ++: An Agile Point Cloud Importance Measure for Robust Classification, Adversarial Defense and Explainable AI

The ability to cope accurately and fast with Out-Of-Distribution (OOD) s...

PointMask: Towards Interpretable and Bias-Resilient Point Cloud Processing

Deep classifiers tend to associate a few discriminative input variables ...

Deflecting 3D Adversarial Point Clouds Through Outlier-Guided Removal

Neural networks are vulnerable to adversarial examples, which poses a th...

Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning

We show that denoising of 3D point clouds can be learned unsupervised, d...

Sparse 3D Point-cloud Map Upsampling and Noise Removal as a vSLAM Post-processing Step: Experimental Evaluation

The monocular vision-based simultaneous localization and mapping (vSLAM)...

Please sign up or login with your details

Forgot password? Click here to reset