Semantic Segmentation for Point Cloud Scenes via Dilated Graph Feature Aggregation and Pyramid Decoders

by   Yongqiang Mao, et al.

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.


page 3

page 6

page 7

page 10


Beyond single receptive field: A receptive field fusion-and-stratification network for airborne laser scanning point cloud classification

The classification of airborne laser scanning (ALS) point clouds is a cr...

MRNet: Multiple-Input Receptive Field Network for Large-Scale Point Cloud Segmentation

The size of the input receptive field is one of the most critical aspect...

Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenes

The deficiency of 3D segmentation labels is one of the main obstacles to...

Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning

Hidden features in neural network usually fail to learn informative repr...

Small but Mighty: Enhancing 3D Point Clouds Semantic Segmentation with U-Next Framework

We study the problem of semantic segmentation of large-scale 3D point cl...

Collaborative Receptive Field Learning

The challenge of object categorization in images is largely due to arbit...

DeepPyramid: Enabling Pyramid View and Deformable Pyramid Reception for Semantic Segmentation in Cataract Surgery Videos

Semantic segmentation in cataract surgery has a wide range of applicatio...

Please sign up or login with your details

Forgot password? Click here to reset