RGCNN: Regularized Graph CNN for Point Cloud Segmentation

By Gusi Te, Wei Hu, Zongming Guo, Amin Zheng. ACM Multimedia, 2018

355 citations recorded by the source corpus.

Point cloud, an efficient 3D object representation, has become popular with the development of depth sensing and 3D laser scanning techniques. It has attracted attention in various applications such as 3D tele-presence, navigation for unmanned vehicles and heritage reconstruction. The understanding of point clouds, such as point cloud segmentation, is crucial in exploiting the informative value of point clouds for such applications. Due to the irregularity of the data format, previous deep learning works often convert point clouds to regular 3D voxel grids or collections of images before feeding them into neural networks, which leads to voluminous data and quantization artifacts. In this paper, we instead propose a regularized graph convolutional neural network (RGCNN) that directly consumes point clouds. Leveraging on spectral graph theory, we treat features of points in a point cloud as signals on graph, and define the convolution over graph by Chebyshev polynomial approximation. In particular, we update the graph Laplacian matrix that describes the connectivity of features in each layer according to the corresponding learned features, which adaptively captures the structure of dynamic graphs. Further, we deploy a graph-signal smoothness prior in the loss function, thus regularizing the learning process. Experimental results on the ShapeNet part dataset show that the proposed approach significantly reduces the computational complexity while achieving competitive performance with the state of the art. Also, experiments show RGCNN is much more robust to both noise and point cloud density in comparison with other methods. We further apply RGCNN to point cloud classification and achieve competitive results on ModelNet40 dataset.

Subfields: Computational Mechanics, Environmental Engineering, Geology

View Paper: https://www.semanticscholar.org/paper/04ecc68f27f8adcd986cf86b89861d0766c3feb1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Environmental Engineering

In Geology

Citations in the corpus

Group-Free 3D Object Detection via Transformers (2021, background): “Network architecture for Point Cloud A large set of network architectures [38, 12, 29, 9, 47, 23, 44, 39, 45, 28, 30, 33, 43, 40, 17, 1, 41, 49, 10, 22] have been proposed for various point cloud based learning tasks.”
A Comprehensive Survey on Graph Neural Networks (2019, methodology): “[141], [142], [143] convert point clouds into k-nearest neighbor graphs or superpoint graphs and use ConvGNNs to explore the topological structure.”
DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing (2019, background): “Some other works introduce graph convolutional network to learn over a local graph [49, 46, 25] or geometric elements [23].”
SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences (2019, methodology): “To overcome the limitations of the voxel-based representation, such as the exploding memory consumption when the resolution of the voxel grid increases, more recent approaches either upsample voxel-predictions [53] using a CRF or use different representations, like more efficient spatial subdivision”
Relation-Shape Convolutional Neural Network for Point Cloud Analysis (2019, background): “Graph convolution network is applied on a local graph created by neighboring points [38, 37, 20].”
Reliable Data Distillation on Graph Convolutional Network (2020, methodology): “A simple method [47] to solve this problem is Graph Laplacian Regularization [33] (GLR).”
Graph convolutional networks: a comprehensive review (2019, methodology): “A regularized graph convolutional network model has been proposed for segmentation on point clouds in [88] in which the graph Laplacian is dynamically updated to capture the connectivity of the learned features.”
Learning 3D Semantic Scene Graphs From 3D Indoor Reconstructions (2020, methodology): “[43] use a Graph CNN for semantic segmentation of object parts.”