RGCNN: Regularized Graph CNN for Point Cloud Segmentation

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.

[1]  José Luis Lerma,et al.  Unsupervised robust planar segmentation of terrestrial laser scanner point clouds based on fuzzy clustering methods , 2008 .

[2]  Jianxiong Xiao,et al.  3D ShapeNets: A deep representation for volumetric shapes , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Leonidas J. Guibas,et al.  SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Alán Aspuru-Guzik,et al.  Convolutional Networks on Graphs for Learning Molecular Fingerprints , 2015, NIPS.

[5]  Teng Ma,et al.  Point cloud segmentation through spectral clustering , 2010, The 2nd International Conference on Information Science and Engineering.

[6]  T. Rabbani,et al.  SEGMENTATION OF POINT CLOUDS USING SMOOTHNESS CONSTRAINT , 2006 .

[7]  Jaejoon Lee,et al.  Edge-adaptive transforms for efficient depth map coding , 2010, 28th Picture Coding Symposium.

[8]  F. Scarselli,et al.  A new model for learning in graph domains , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[9]  Xianfeng Huang,et al.  A Methodology for Automated Segmentation and Reconstruction of Urban 3-D Buildings from ALS Point Clouds , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[10]  Nico Blodow,et al.  Towards 3D Point cloud based object maps for household environments , 2008, Robotics Auton. Syst..

[11]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[12]  Leonidas J. Guibas,et al.  A scalable active framework for region annotation in 3D shape collections , 2016, ACM Trans. Graph..

[13]  Joan Bruna,et al.  Spectral Networks and Locally Connected Networks on Graphs , 2013, ICLR.

[14]  Xavier Bresson,et al.  CayleyNets: Graph Convolutional Neural Networks With Complex Rational Spectral Filters , 2017, IEEE Transactions on Signal Processing.

[15]  Mathias Niepert,et al.  Learning Convolutional Neural Networks for Graphs , 2016, ICML.

[16]  Leonidas J. Guibas,et al.  PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Leonidas J. Guibas,et al.  PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space , 2017, NIPS.

[18]  Joan Bruna,et al.  Deep Convolutional Networks on Graph-Structured Data , 2015, ArXiv.

[19]  Sebastian Scherer,et al.  VoxNet: A 3D Convolutional Neural Network for real-time object recognition , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[20]  Pierre Vandergheynst,et al.  Wavelets on Graphs via Spectral Graph Theory , 2009, ArXiv.

[21]  Oscar C. Au,et al.  Multiresolution Graph Fourier Transform for Compression of Piecewise Smooth Images , 2015, IEEE Transactions on Image Processing.

[22]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[23]  Yue Wang,et al.  Dynamic Graph CNN for Learning on Point Clouds , 2018, ACM Trans. Graph..

[24]  Horst Bunke,et al.  Fast range image segmentation using high-level segmentation primitives , 1996, Proceedings Third IEEE Workshop on Applications of Computer Vision. WACV'96.

[25]  Subhransu Maji,et al.  Multi-view Convolutional Neural Networks for 3D Shape Recognition , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[26]  U. Feige,et al.  Spectral Graph Theory , 2015 .

[27]  S. Filin SURFACE CLUSTERING FROM AIRBORNE LASER SCANNING DATA , 2002 .

[28]  P. Vandergheynst,et al.  Accelerated filtering on graphs using Lanczos method , 2015, 1509.04537.

[29]  Sagi Filin,et al.  AN ENERGY-BASED APPROACH FOR DETECTION AND CHARACTERIZATION OF SUBTLE ENTITIES WITHIN LASER SCANNING POINT-CLOUDS , 2016 .

[30]  Rufael Mekuria,et al.  Use cases for point cloud compression (PCC) , 2016 .

[31]  Oscar C. Au,et al.  Depth map compression using multi-resolution graph-based transform for depth-image-based rendering , 2012, 2012 19th IEEE International Conference on Image Processing.

[32]  Yin Zhou,et al.  VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[33]  F. Tarsha-Kurdi,et al.  Hough-Transform and Extended RANSAC Algorithms for Automatic Detection of 3D Building Roof Planes from Lidar Data , 2007 .