Cross-Level Cross-Scale Cross-Attention Network for Point Cloud Representation

TL;DR

This paper introduces CLCSCANet, an innovative attention-based architecture that hierarchically extracts and models multi-scale point cloud features, significantly improving 3D object classification and segmentation performance.

Contribution

The paper proposes a novel end-to-end network with cross-level and cross-scale attention modules for enhanced point cloud representation learning.

Findings

Achieves competitive results on 3D classification tasks

Effectively models inter- and intra-scale dependencies

Outperforms existing methods in segmentation accuracy

Abstract

Self-attention mechanism recently achieves impressive advancement in Natural Language Processing (NLP) and Image Processing domains. And its permutation invariance property makes it ideally suitable for point cloud processing. Inspired by this remarkable success, we propose an end-to-end architecture, dubbed Cross-Level Cross-Scale Cross-Attention Network (CLCSCANet), for point cloud representation learning. First, a point-wise feature pyramid module is introduced to hierarchically extract features from different scales or resolutions. Then a cross-level cross-attention is designed to model long-range inter-level and intra-level dependencies. Finally, we develop a cross-scale cross-attention module to capture interactions between-and-within scales for representation enhancement. Compared with state-of-the-art approaches, our network can obtain competitive performance on challenging 3D object classification, point cloud segmentation tasks via comprehensive experimental evaluation.