Enhancing point cloud analysis via neighbor aggregation correction based on cross-stage structure correlation

TL;DR

This paper introduces PDSA, a novel point cloud feature aggregation method that improves efficiency and robustness by correcting neighbor features through high-dimensional correlation, enhancing segmentation and classification accuracy.

Contribution

The paper proposes PDSA, a lightweight module that utilizes high-dimensional correlation for neighbor feature correction, addressing noise and hierarchy gaps in point cloud analysis.

Findings

Significant performance improvements on semantic segmentation and classification tasks.

Reduced parameter cost and increased robustness compared to baseline methods.

Effective feature correction demonstrated through ablation and visualization studies.

Abstract

Point cloud analysis is the cornerstone of many downstream tasks, among which aggregating local structures is the basis for understanding point cloud data. While numerous works aggregate neighbor using three-dimensional relative coordinates, there are irrelevant point interference and feature hierarchy gap problems due to the limitation of local coordinates. Although some works address this limitation by refining spatial description though explicit modeling of cross-stage structure, these enhancement methods based on direct geometric structure encoding have problems of high computational overhead and noise sensitivity. To overcome these problems, we propose the Point Distribution Set Abstraction module (PDSA) that utilizes the correlation in the high-dimensional space to correct the feature distribution during aggregation, which improves the computational efficiency and robustness. PDSA distinguishes the point correlation based on a lightweight cross-stage structural descriptor, and enhances structural homogeneity by reducing the variance of the neighbor feature matrix and increasing classes separability though long-distance modeling. Additionally, we introducing a key point mechanism to optimize the computational overhead. The experimental result on semantic segmentation and classification tasks based on different baselines verify the generalization of the method we proposed, and achieve significant performance improvement with less parameter cost. The corresponding ablation and visualization results demonstrate the effectiveness and rationality of our method. The code and training weight is available at: https://github.com/AGENT9717/PointDistribution