Enhancing Sampling Protocol for Point Cloud Classification Against Corruptions

TL;DR

PointSP tackles the vulnerability of traditional point cloud sampling (FPS/FSS) to real-world corruptions by introducing a learning-free protocol that combines point reweighting (isolation rate), FFPS for inference-time outlier filtering, and training-time full-points resampling with a local-global balanced downsampling and tangent-plane interpolation for density growth. It operates without architecture changes, enhancing robustness across synthetic and real corrupted datasets and multiple 3D backbones. Experimental results on ModelNet40-C, PointCloud-C, and OmniObject-C show substantial improvements in mean error rate (about 10% reductions) and better segmentation performance, validating practical impact for applications like autonomous driving. The method emphasizes easy integration, computational efficiency, and applicability across classification and segmentation tasks in corrupted 3D data scenarios.

Abstract

Established sampling protocols for 3D point cloud learning, such as Farthest Point Sampling (FPS) and Fixed Sample Size (FSS), have long been relied upon. However, real-world data often suffer from corruptions, such as sensor noise, which violates the benign data assumption in current protocols. As a result, these protocols are highly vulnerable to noise, posing significant safety risks in critical applications like autonomous driving. To address these issues, we propose an enhanced point cloud sampling protocol, PointSP, designed to improve robustness against point cloud corruptions. PointSP incorporates key point reweighting to mitigate outlier sensitivity and ensure the selection of representative points. It also introduces a local-global balanced downsampling strategy, which allows for scalable and adaptive sampling while maintaining geometric consistency. Additionally, a lightweight tangent plane interpolation method is used to preserve local geometry while enhancing the density of the point cloud. Unlike learning-based approaches that require additional model training, PointSP is architecture-agnostic, requiring no extra learning or modification to the network. This enables seamless integration into existing pipelines. Extensive experiments on synthetic and real-world corrupted datasets show that PointSP significantly improves the robustness and accuracy of point cloud classification, outperforming state-of-the-art methods across multiple benchmarks.

Figures (7)

• Figure 1: The first row presents the original point clouds, while the second row highlights the sampled key points, with those selected by farthest point sampling (FPS) shown in red. The existing standard sampling protocol is not optimized for corrupted point cloud in practice. As a result, a standard-trained PointNet classifies them as Chair, Vase, Table, Mantel, and Sofa. Towards this issue, we propose to enhance the protocol by revising FPS into new key points selections and integrating full points resampling into process.
• Figure 2: PointSP: enhanced protocol of point cloud sampling for robust classification. The existing and conventional protocol used farthest point sampling (FPS) and non-processed points for input. In our protocol, randomized key point sampling and full points resampling (random up& downsampling) are used in training to conduct sampling-based data augmentation. During inference, filtered FPS (FFPS) is implemented to bypass outliers, and an upsampling strategy is used to densify sparse input. We propose the concept of isolation rate, the upsampling by tangent plane interpolation and the local-global balanced downsampling to obtain point weights and resampled points, respectively.
• Figure 3: Instance mean IoU (left) and overall accuracy (right) on ShapeNet-C.
• Figure 4: mERs of FFPS's different threshold $\omega$ on ModelNet40-C (left) and PointCloud-C (right).
• Figure 5: Visualization of point-wise Isolation Rate. Lower isolation rate Column 1 presents the clean data, while Columns 2 to 5 depict data with the corresponding corruption types indicated above each column.