GAM : Gradient Attention Module of Optimization for Point Clouds Analysis

TL;DR

This paper introduces the Gradient Attention Module (GAM), a novel local feature aggregation method for point cloud analysis that leverages geometric gradient information to improve accuracy and robustness.

Contribution

The paper proposes GAM, which simplifies gradient extraction and uses explicit angle matrices, significantly accelerating local feature aggregation in point cloud processing.

Findings

GAM accelerates processing by 35 times.

GAM achieves state-of-the-art results on S3DIS dataset.

GAM demonstrates strong generalization across five benchmark datasets.

Abstract

In point cloud analysis tasks, the existing local feature aggregation descriptors (LFAD) are unable to fully utilize information in the neighborhood of central points. Previous methods rely solely on Euclidean distance to constrain the local aggregation process, which can be easily affected by abnormal points and cannot adequately fit with the original geometry of the point cloud. We believe that fine-grained geometric information (FGGI) is significant for the aggregation of local features. Therefore, we propose a gradient-based local attention module, termed as Gradient Attention Module (GAM), to address the aforementioned problem. Our proposed GAM simplifies the process that extracts gradient information in the neighborhood and uses the Zenith Angle matrix and Azimuth Angle matrix as explicit representation, which accelerates the module by 35X. Comprehensive experiments were conducted on five benchmark datasets to demonstrate the effectiveness and generalization capability of the proposed GAM for 3D point cloud analysis. Especially on S3DIS dataset, GAM achieves the best performance among current point-based models with mIoU/OA/mAcc of 74.4%/90.6%/83.2%, respectively.