SWCF-Net: Similarity-weighted Convolution and Local-global Fusion for Efficient Large-scale Point Cloud Semantic Segmentation

TL;DR

SWCF-Net is a novel neural network that efficiently combines local and global features for large-scale point cloud semantic segmentation, leveraging similarity-weighted convolution and a linearized attention mechanism.

Contribution

The paper introduces SWCF-Net, which effectively integrates local and global features using similarity-weighted convolution and a low-complexity attention mechanism for large-scale point cloud segmentation.

Findings

Achieves competitive accuracy on SemanticKITTI and Toronto3D datasets.

Reduces computational complexity from quadratic to linear in attention modules.

Effectively handles large-scale point clouds with less computational cost.

Abstract

Large-scale point cloud consists of a multitude of individual objects, thereby encompassing rich structural and underlying semantic contextual information, resulting in a challenging problem in efficiently segmenting a point cloud. Most existing researches mainly focus on capturing intricate local features without giving due consideration to global ones, thus failing to leverage semantic context. In this paper, we propose a Similarity-Weighted Convolution and local-global Fusion Network, named SWCF-Net, which takes into account both local and global features. We propose a Similarity-Weighted Convolution (SWConv) to effectively extract local features, where similarity weights are incorporated into the convolution operation to enhance the generalization capabilities. Then, we employ a downsampling operation on the K and V channels within the attention module, thereby reducing the quadratic complexity to linear, enabling the Transformer to deal with large-scale point clouds. At last, orthogonal components are extracted in the global features and then aggregated with local features, thereby eliminating redundant information between local and global features and consequently promoting efficiency. We evaluate SWCF-Net on large-scale outdoor datasets SemanticKITTI and Toronto3D. Our experimental results demonstrate the effectiveness of the proposed network. Our method achieves a competitive result with less computational cost, and is able to handle large-scale point clouds efficiently.