Semantic Segmentation for Point Cloud Scenes via Dilated Graph Feature Aggregation and Pyramid Decoders
This work addresses a domain-specific problem in 3D computer vision for applications like autonomous driving and robotics, with incremental improvements over existing methods.
The paper tackled the challenge of semantic segmentation in point clouds, particularly the misclassification of instances with similar spatial structures, by proposing DGFA-Net with dilated graph feature aggregation and pyramid decoders, achieving new state-of-the-art performance on datasets like S3DIS, ShapeNetPart, and Toronto-3D.
Semantic segmentation of point clouds generates comprehensive understanding of scenes through densely predicting the category for each point. Due to the unicity of receptive field, semantic segmentation of point clouds remains challenging for the expression of multi-receptive field features, which brings about the misclassification of instances with similar spatial structures. In this paper, we propose a graph convolutional network DGFA-Net rooted in dilated graph feature aggregation (DGFA), guided by multi-basis aggregation loss (MALoss) calculated through Pyramid Decoders. To configure multi-receptive field features, DGFA which takes the proposed dilated graph convolution (DGConv) as its basic building block, is designed to aggregate multi-scale feature representation by capturing dilated graphs with various receptive regions. By simultaneously considering penalizing the receptive field information with point sets of different resolutions as calculation bases, we introduce Pyramid Decoders driven by MALoss for the diversity of receptive field bases. Combining these two aspects, DGFA-Net significantly improves the segmentation performance of instances with similar spatial structures. Experiments on S3DIS, ShapeNetPart and Toronto-3D show that DGFA-Net outperforms the baseline approach, achieving a new state-of-the-art segmentation performance.