Density-aware global-local attention network for point cloud segmentation

TL;DR

This paper introduces a density-aware global-local attention network for point cloud segmentation, effectively handling small objects and categories with limited samples by combining local density-based attention with global context.

Contribution

The proposed network fuses local density-aware attention with global attention and introduces a category-response loss, improving segmentation of small objects and rare categories.

Findings

Achieves competitive results on multiple datasets.

Demonstrates strong performance on real-world scenes with tiny objects.

Effectively balances category and size variations in segmentation.

Abstract

3D point cloud segmentation has a wide range of applications in areas such as autonomous driving, augmented reality, virtual reality and digital twins. The point cloud data collected in real scenes often contain small objects and categories with small sample sizes, which are difficult to handle by existing networks. In this regard, we propose a point cloud segmentation network that fuses local attention based on density perception with global attention. The core idea is to increase the effective receptive field of each point while reducing the loss of information about small objects in dense areas. Specifically, we divide different sized windows for local areas with different densities to compute attention within the window. Furthermore, we consider each local area as an independent token for the global attention of the entire input. A category-response loss is also proposed to balance the processing of different categories and sizes of objects. In particular, we set up an additional fully connected layer in the middle of the network for prediction of the presence of object categories, and construct a binary cross-entropy loss to respond to the presence of categories in the scene. In experiments, our method achieves competitive results in semantic segmentation and part segmentation tasks on several publicly available datasets. Experiments on point cloud data obtained from complex real-world scenes filled with tiny objects also validate the strong segmentation capability of our method for small objects as well as small sample categories.