pCTFusion: Point Convolution-Transformer Fusion with Semantic Aware Loss for Outdoor LiDAR Point Cloud Segmentation

TL;DR

pCTFusion introduces a novel architecture combining point convolution and self-attention with a new loss function, significantly improving outdoor LiDAR point cloud segmentation accuracy, especially for minor classes.

Contribution

The paper proposes pCTFusion, a new model that fuses convolution and self-attention mechanisms with a semantic-aware loss for enhanced segmentation performance.

Findings

Achieved 5-7% performance improvement on SemanticKITTI dataset.

Enhanced accuracy for minor classes with class imbalance.

Demonstrated effectiveness of combined local and global attention mechanisms.

Abstract

LiDAR-generated point clouds are crucial for perceiving outdoor environments. The segmentation of point clouds is also essential for many applications. Previous research has focused on using self-attention and convolution (local attention) mechanisms individually in semantic segmentation architectures. However, there is limited work on combining the learned representations of these attention mechanisms to improve performance. Additionally, existing research that combines convolution with self-attention relies on global attention, which is not practical for processing large point clouds. To address these challenges, this study proposes a new architecture, pCTFusion, which combines kernel-based convolutions and self-attention mechanisms for better feature learning and capturing local and global dependencies in segmentation. The proposed architecture employs two types of self-attention mechanisms, local and global, based on the hierarchical positions of the encoder blocks. Furthermore, the existing loss functions do not consider the semantic and position-wise importance of the points, resulting in reduced accuracy, particularly at sharp class boundaries. To overcome this, the study models a novel attention-based loss function called Pointwise Geometric Anisotropy (PGA), which assigns weights based on the semantic distribution of points in a neighborhood. The proposed architecture is evaluated on SemanticKITTI outdoor dataset and showed a 5-7% improvement in performance compared to the state-of-the-art architectures. The results are particularly encouraging for minor classes, often misclassified due to class imbalance, lack of space, and neighbor-aware feature encoding. These developed methods can be leveraged for the segmentation of complex datasets and can drive real-world applications of LiDAR point cloud.