BAGNet: A Boundary-Aware Graph Attention Network for 3D Point Cloud Semantic Segmentation
This work addresses computational efficiency for researchers and practitioners in 3D computer vision, though it appears incremental as it builds on existing graph attention networks.
The paper tackles the challenge of high computational cost in graph-based 3D point cloud semantic segmentation by proposing BAGNet, which focuses on boundary points to reduce computation time while maintaining accuracy, achieving higher accuracy and less inference time compared to state-of-the-art methods.
Since the point cloud data is inherently irregular and unstructured, point cloud semantic segmentation has always been a challenging task. The graph-based method attempts to model the irregular point cloud by representing it as a graph; however, this approach incurs substantial computational cost due to the necessity of constructing a graph for every point within a large-scale point cloud. In this paper, we observe that boundary points possess more intricate spatial structural information and develop a novel graph attention network known as the Boundary-Aware Graph attention Network (BAGNet). On one hand, BAGNet contains a boundary-aware graph attention layer (BAGLayer), which employs edge vertex fusion and attention coefficients to capture features of boundary points, reducing the computation time. On the other hand, BAGNet employs a lightweight attention pooling layer to extract the global feature of the point cloud to maintain model accuracy. Extensive experiments on standard datasets demonstrate that BAGNet outperforms state-of-the-art methods in point cloud semantic segmentation with higher accuracy and less inference time.