EPiC: Ensemble of Partial Point Clouds for Robust Classification

TL;DR

EPiC introduces an ensemble framework that enhances the robustness of point cloud classification against partial and noisy data by employing diverse sampling strategies, achieving state-of-the-art results on ModelNet-C.

Contribution

The paper presents a novel ensemble method based on partial point cloud sampling strategies to improve robustness in 3D classification tasks.

Findings

Significant reduction in Corruption Error on ModelNet-C dataset.

Outperforms existing methods on both unaugmented and augmented data.

Demonstrates the effectiveness of diverse sampling strategies for robustness.

Abstract

Robust point cloud classification is crucial for real-world applications, as consumer-type 3D sensors often yield partial and noisy data, degraded by various artifacts. In this work we propose a general ensemble framework, based on partial point cloud sampling. Each ensemble member is exposed to only partial input data. Three sampling strategies are used jointly, two local ones, based on patches and curves, and a global one of random sampling. We demonstrate the robustness of our method to various local and global degradations. We show that our framework significantly improves the robustness of top classification netowrks by a large margin. Our experimental setting uses the recently introduced ModelNet-C database by Ren et al.[24], where we reach SOTA both on unaugmented and on augmented data. Our unaugmented mean Corruption Error (mCE) is 0.64 (current SOTA is 0.86) and 0.50 for augmented data (current SOTA is 0.57). We analyze and explain these remarkable results through diversity analysis. Our code is available at: https://github.com/yossilevii100/EPiC