GFPNet: A Deep Network for Learning Shape Completion in Generic Fitted Primitives

In this letter, we propose an object reconstruction apparatus that uses the so-called Generic Primitives (GP) to complete shapes. A GP is a 3D point cloud depicting a generalized shape of a class of objects. To reconstruct the objects in a scene we first fit a GP onto each occluded object to obtain an initial raw structure. Secondly, we use a model-based deformation technique to fold the surface of the GP over the occluded object. The deformation model is encoded within the layers of a Deep Neural Network (DNN), coined GFPNet. The objective of the network is to transfer the particularities of the object from the scene to the raw volume represented by the GP. We show that GFPNet competes with state of the art shape completion methods by providing performance results on the ModelNet and KITTI benchmarking datasets.

[1]  Duc Thanh Nguyen,et al.  A Field Model for Repairing 3D Shapes , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Sebastian Thrun,et al.  Shape from symmetry , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[3]  Derek Hoiem,et al.  Completing 3D object shape from one depth image , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Andreas Geiger,et al.  Vision meets robotics: The KITTI dataset , 2013, Int. J. Robotics Res..

[5]  Leonidas J. Guibas,et al.  Data-driven structural priors for shape completion , 2015, ACM Trans. Graph..

[6]  Ian D. Reid,et al.  Dense Reconstruction Using 3D Object Shape Priors , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  J. Diebold.  Automation , 1955, Industry, Innovation and Infrastructure.

[8]  Martial Hebert,et al.  PCN: Point Completion Network , 2018, 2018 International Conference on 3D Vision (3DV).

[9]  Niloy J. Mitra,et al.  Learning Semantic Deformation Flows with 3D Convolutional Networks , 2016, ECCV.

[10]  Dong Tian,et al.  FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds , 2017, ArXiv.

[11]  Jörg Stückler,et al.  Joint Object Pose Estimation and Shape Reconstruction in Urban Street Scenes Using 3D Shape Priors , 2016, GCPR.

[12]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[13]  Leonidas J. Guibas,et al.  ShapeNet: An Information-Rich 3D Model Repository , 2015, ArXiv.

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

[15]  Xiaogang Wang,et al.  PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Leonidas J. Guibas,et al.  Example-Based 3D Scan Completion , 2005 .

[17]  Matthias Nießner,et al.  Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Chad DeChant,et al.  Shape completion enabled robotic grasping , 2016, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[19]  J. Ahlberg.  Active Contours in Three Dimensions , 1996 .

[20]  D. Levin,et al.  Mesh-Independent Surface Interpolation , 2004 .

[21]  Andreas Geiger,et al.  Learning 3D Shape Completion Under Weak Supervision , 2018, International Journal of Computer Vision.

[22]  Minh N. Do,et al.  RGB-D Object-to-CAD Retrieval , 2018, 3DOR@Eurographics.

[23]  Andreas Geiger,et al.  Displets: Resolving stereo ambiguities using object knowledge , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[25]  Andreas Geiger,et al.  Learning 3D Shape Completion from Laser Scan Data with Weak Supervision , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[26]  Bernhard Schölkopf,et al.  Support Vector Machines for 3D Shape Processing , 2005, Comput. Graph. Forum.

[27]  Jörg Stückler,et al.  SAMP: Shape and Motion Priors for 4D Vehicle Reconstruction , 2017, 2017 IEEE Winter Conference on Applications of Computer Vision (WACV).

[28]  Bogdan Trasnea,et al.  NeuroTrajectory: A Neuroevolutionary Approach to Local State Trajectory Learning for Autonomous Vehicles , 2019, IEEE Robotics and Automation Letters.

[29]  Sorin Mihai Grigorescu,et al.  Generic fitted shapes (GFS): Volumetric object segmentation in service robotics , 2013, Robotics Auton. Syst..

[30]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[31]  Howie Choset,et al.  PCRNet: Point Cloud Registration Network using PointNet Encoding , 2019, ArXiv.

[32]  Sorin Mihai Grigorescu,et al.  3D Structure Estimation from a Single View Using Generic Fitted Primitives (GFP) , 2012, VISIGRAPP.