Self-Supervised Learning of Part Mobility from Point Cloud Sequence

Part mobility analysis is a significant aspect required to achieve a functional understanding of 3D objects. It would be natural to obtain part mobility from the continuous part motion of 3D objects. In this study, we introduce a self-supervised method for segmenting motion parts and predicting their motion attributes from a point cloud sequence representing a dynamic object. To sufficiently utilize spatiotemporal information from the point cloud sequence, we generate trajectories by using correlations among successive frames of the sequence instead of directly processing the point clouds. We propose a novel neural network architecture called PointRNN to learn feature representations of trajectories along with their part rigid motions. We evaluate our method on various tasks including motion part segmentation, motion axis prediction and motion range estimation. The results demonstrate that our method outperforms previous techniques on both synthetic and real datasets. Moreover, our method has the ability to generalize to new and unseen objects. It is important to emphasize that it is not required to know any prior shape structure, prior shape category information, or shape orientation. To the best of our knowledge, this is the first study on deep learning to extract part mobility from point cloud sequence of a dynamic object.

[1]  James M. Rehg,et al.  Learning contact locations for pushing and orienting unknown objects , 2013, 2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids).

[2]  Jeannette Bohg,et al.  MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[3]  Andriy Myronenko,et al.  On the closed-form solution of the rotation matrix arising in computer vision problems , 2009, ArXiv.

[4]  Ariel Shamir,et al.  Learning to predict part mobility from a single static snapshot , 2017, ACM Trans. Graph..

[5]  Jonathan Tompson,et al.  Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning , 2018, NeurIPS.

[6]  Sang Chul Ahn,et al.  Simultaneous segmentation, estimation and analysis of articulated motion from dense point cloud sequence , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[7]  Matthias Zwicker,et al.  Automatic Registration for Articulated Shapes , 2008, Comput. Graph. Forum.

[8]  Lourdes Agapito,et al.  Automated articulated structure and 3D shape recovery from point correspondences , 2011, 2011 International Conference on Computer Vision.

[9]  Daniel Cremers,et al.  A primal-dual framework for real-time dense RGB-D scene flow , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[10]  Wei Wu,et al.  PointCNN: Convolution On X-Transformed Points , 2018, NeurIPS.

[11]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Leonidas J. Guibas,et al.  PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[14]  Hui Huang,et al.  RPM-Net , 2019, ACM Trans. Graph..

[15]  Leonidas J. Guibas,et al.  FlowNet3D: Learning Scene Flow in 3D Point Clouds , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Hao Li,et al.  Mobility Fitting using 4D RANSAC , 2016, Comput. Graph. Forum.

[17]  Xiaogang Wang,et al.  Shape2Motion: Joint Analysis of Motion Parts and Attributes From 3D Shapes , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Rama Chellappa,et al.  3DRegNet: A Deep Neural Network for 3D Point Registration , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Oliver Brock,et al.  The RBO dataset of articulated objects and interactions , 2018, Int. J. Robotics Res..

[20]  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).

[21]  Wilmot Li,et al.  Illustrating how mechanical assemblies work , 2010, SIGGRAPH 2010.

[22]  Leonidas J. Guibas,et al.  Deep part induction from articulated object pairs , 2018, ACM Trans. Graph..

[23]  Yiannis Aloimonos,et al.  Affordance detection of tool parts from geometric features , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[24]  Scott Schaefer,et al.  Image deformation using moving least squares , 2006, ACM Trans. Graph..

[25]  Oliver van Kaick,et al.  Functionality Representations and Applications for Shape Analysis , 2018, Comput. Graph. Forum.

[26]  Konrad Schindler,et al.  View-Consistent 3D Scene Flow Estimation over Multiple Frames , 2014, ECCV.

[27]  Leonidas J. Guibas,et al.  SAPIEN: A SimulAted Part-Based Interactive ENvironment , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[29]  Kai Xu,et al.  Recurrent 3D attentional networks for end-to-end active object recognition , 2019, Computational Visual Media.

[30]  Marc Pollefeys,et al.  A General Framework for Motion Segmentation: Independent, Articulated, Rigid, Non-rigid, Degenerate and Non-degenerate , 2006, ECCV.

[31]  Marc Alexa,et al.  As-rigid-as-possible surface modeling , 2007, Symposium on Geometry Processing.

[32]  Ken-ichi Anjyo,et al.  Optimal and interactive keyframe selection for motion capture , 2018, SIGGRAPH Asia Technical Briefs.

[33]  Sebastian Scherer,et al.  3D Convolutional Neural Networks for landing zone detection from LiDAR , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[34]  Hui Huang,et al.  Space‐Time Co‐Segmentation of Articulated Point Cloud Sequences , 2016, Comput. Graph. Forum.

[35]  Aseem Behl,et al.  PointFlowNet: Learning Representations for Rigid Motion Estimation From Point Clouds , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Wilmot Li,et al.  Illustrating how mechanical assemblies work , 2010, CACM.

[37]  Darius Burschka,et al.  Deformable 3D Shape Registration Based on Local Similarity Transforms , 2011, Comput. Graph. Forum.