Cascaded Non-local Neural Network for Point Cloud Semantic Segmentation

TL;DR

This paper introduces a cascaded non-local neural network that captures long-range dependencies in point clouds for improved semantic segmentation, achieving state-of-the-art results with reduced computational costs.

Contribution

It proposes a novel cascaded non-local module with neighborhood, superpoint, and global levels, enhancing segmentation accuracy and efficiency.

Findings

Achieves state-of-the-art segmentation performance on multiple datasets.

Reduces computational cost and memory usage compared to traditional non-local methods.

Effectively propagates geometric information across different neighborhood scales.

Abstract

In this paper, we propose a cascaded non-local neural network for point cloud segmentation. The proposed network aims to build the long-range dependencies of point clouds for the accurate segmentation. Specifically, we develop a novel cascaded non-local module, which consists of the neighborhood-level, superpoint-level and global-level non-local blocks. First, in the neighborhood-level block, we extract the local features of the centroid points of point clouds by assigning different weights to the neighboring points. The extracted local features of the centroid points are then used to encode the superpoint-level block with the non-local operation. Finally, the global-level block aggregates the non-local features of the superpoints for semantic segmentation in an encoder-decoder framework. Benefiting from the cascaded structure, geometric structure information of different neighborhoods with the same label can be propagated. In addition, the cascaded structure can largely reduce the computational cost of the original non-local operation on point clouds. Experiments on different indoor and outdoor datasets show that our method achieves state-of-the-art performance and effectively reduces the time consumption and memory occupation.