A Deep Learnable Framework for 3D Point Clouds Pose Transformation Regression

Object detection and classification for point clouds with deep learning module has gained some substantial progress recently. But there is still a blank for spatial transformation estimation like rigid pose regression with learnable module for point clouds, comparing with other kinds of 2D feature format like range images or RGB images. In this paper, we present a complete framework for point cloud pose regression with the deep learnable module. The method for feeding unordered 3D point clouds to a feature map like 2D images is using the symmetric function, which is the state of the art for object segmentation and classification. The pose regression idea take advantage of the spatial transformation of feature map with neural networks, converging both classification loss and pose regression loss function. We augmented the synthetic sample data by apply randomly sampled rigid pose transformation and Gaussian noise. The whole idea of this study is intuitive and straightforward and we show that the deep learnable module can reduce the rigid transformation loss and the potential application in many fields.

[1]  Leonidas J. Guibas,et al.  Volumetric and Multi-view CNNs for Object Classification on 3D Data , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  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).

[3]  Nico Blodow,et al.  Fast Point Feature Histograms (FPFH) for 3D registration , 2009, 2009 IEEE International Conference on Robotics and Automation.

[4]  Andrew Zisserman,et al.  Spatial Transformer Networks , 2015, NIPS.

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

[6]  Victor S. Lempitsky,et al.  Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[7]  Jun Cheng,et al.  Registration for 3-D point cloud using angular-invariant feature , 2009, Neurocomputing.

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

[9]  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).

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

[11]  Tomas Pfister,et al.  Learning from Simulated and Unsupervised Images through Adversarial Training , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Nassir Navab,et al.  Model globally, match locally: Efficient and robust 3D object recognition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Roberto Cipolla,et al.  PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).