Supervised Fitting of Geometric Primitives to 3D Point Clouds

Fitting geometric primitives to 3D point cloud data bridges a gap between low-level digitized 3D data and high-level structural information on the underlying 3D shapes. As such, it enables many downstream applications in 3D data processing. For a long time, RANSAC-based methods have been the gold standard for such primitive fitting problems, but they require careful per-input parameter tuning and thus do not scale well for large datasets with diverse shapes. In this work, we introduce Supervised Primitive Fitting Network (SPFN), an end-to-end neural network that can robustly detect a varying number of primitives at different scales without any user control. The network is supervised using ground truth primitive surfaces and primitive membership for the input points. Instead of directly predicting the primitives, our architecture first predicts per-point properties and then uses a differential model estimation module to compute the primitive type and parameters. We evaluate our approach on a novel benchmark of ANSI 3D mechanical component models and demonstrate a significant improvement over both the state-of-the-art RANSAC-based methods and the direct neural prediction.

[1]  D. Marr,et al.  Representation and recognition of the spatial organization of three-dimensional shapes , 1978, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[2]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[3]  Ralph R. Martin,et al.  Faithful Least-Squares Fitting of Spheres, Cylinders, Cones and Tori for Reliable Segmentation , 1998, ECCV.

[4]  Andrew Zisserman,et al.  MLESAC: A New Robust Estimator with Application to Estimating Image Geometry , 2000, Comput. Vis. Image Underst..

[5]  Jiri Matas,et al.  Randomized RANSAC with T(d, d) test , 2002, BMVC.

[6]  Marc Pouget,et al.  Estimating differential quantities using polynomial fitting of osculating jets , 2003, Comput. Aided Geom. Des..

[7]  Jiri Matas,et al.  Randomized RANSAC with Td, d test , 2004, Image Vis. Comput..

[8]  Jiri Matas,et al.  Matching with PROSAC - progressive sample consensus , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[9]  Reinhard Klein,et al.  Efficient RANSAC for Point‐Cloud Shape Detection , 2007, Comput. Graph. Forum.

[10]  Z Ansi,et al.  American National Standards Institute (ANSI) , 2009, Encyclopedia of Biometrics.

[11]  Harold W. Kuhn,et al.  The Hungarian method for the assignment problem , 1955, 50 Years of Integer Programming.

[12]  Daniel Cohen-Or,et al.  GlobFit: consistently fitting primitives by discovering global relations , 2011, ACM Trans. Graph..

[13]  Vladlen Koltun,et al.  Parameter Learning and Convergent Inference for Dense Random Fields , 2013, ICML.

[14]  Cristian Sminchisescu,et al.  Matrix Backpropagation for Deep Networks with Structured Layers , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[15]  Zhen Li,et al.  Primitive Fitting Based on the Efficient multiBaySAC Algorithm , 2015, PloS one.

[16]  Cristian Sminchisescu,et al.  Training Deep Networks with Structured Layers by Matrix Backpropagation , 2015, ArXiv.

[17]  Abhinav Gupta,et al.  Marr Revisited: 2D-3D Alignment via Surface Normal Prediction , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  C. Qi.  Deep Learning on Point Sets for 3 D Classification and Segmentation , 2016 .

[19]  Iain Murray,et al.  Differentiation of the Cholesky decomposition , 2016, ArXiv.

[20]  Eric Brachmann,et al.  DSAC — Differentiable RANSAC for Camera Localization , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Abdul Nurunnabi,et al.  ROBUST CYLINDER FITTING IN THREE-DIMENSIONAL POINT CLOUD DATA , 2017 .

[22]  Ersin Yumer,et al.  3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

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

[24]  Leonidas J. Guibas,et al.  Learning Shape Abstractions by Assembling Volumetric Primitives , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  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).

[26]  Maks Ovsjanikov,et al.  PCPNet Learning Local Shape Properties from Raw Point Clouds , 2017, Comput. Graph. Forum.

[27]  Vladlen Koltun,et al.  Deep Fundamental Matrix Estimation , 2018, ECCV.

[28]  Subhransu Maji,et al.  CSGNet: Neural Shape Parser for Constructive Solid Geometry , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[29]  Leonidas J. Guibas,et al.  Deep Functional Dictionaries: Learning Consistent Semantic Structures on 3D Models from Functions , 2018, NeurIPS.

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

[31]  J. Wang,et al.  Constructing 3D CSG Models from 3D Raw Point Clouds , 2018, Comput. Graph. Forum.

[32]  Leonidas J. Guibas,et al.  Parsing Geometry Using Structure-Aware Shape Templates , 2018, 2018 International Conference on 3D Vision (3DV).

[33]  Tamy Boubekeur,et al.  A Survey of Simple Geometric Primitives Detection Methods for Captured 3D Data , 2018, Comput. Graph. Forum.