Differentiable Iterative Surface Normal Estimation

This paper presents an end-to-end differentiable algorithm for anisotropic surface normal estimation on unstructured point-clouds. We utilize graph neural networks to iteratively infer point weights for a plane fitting algorithm applied to local neighborhoods. The approach retains the interpretability and efficiency of traditional sequential plane fitting while benefiting from a data-dependent deep-learning parameterization. This results in a state-of-the-art surface normal estimator that is robust to noise, outliers and point density variation and that preserves sharp features through anisotropic kernels and a local spatial transformer. Contrary to previous deep learning methods, the proposed approach does not require any hand-crafted features while being faster and more parameter efficient.

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

[2]  Slobodan Ilic,et al.  PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors , 2018, ECCV.

[3]  Renjie Liao,et al.  GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[5]  Rob Fergus,et al.  Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[6]  Leonidas J. Guibas,et al.  Learning Transformation Synchronization , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Michael M. Kazhdan,et al.  Poisson surface reconstruction , 2006, SGP '06.

[8]  Jure Leskovec,et al.  Representation Learning on Graphs: Methods and Applications , 2017, IEEE Data Eng. Bull..

[9]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[10]  Pierre Vandergheynst,et al.  Geometric Deep Learning: Going beyond Euclidean data , 2016, IEEE Signal Process. Mag..

[11]  Tony DeRose,et al.  Surface reconstruction from unorganized points , 1992, SIGGRAPH.

[12]  Martin Grohe,et al.  Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks , 2018, AAAI.

[13]  M. Giles.  Collected Matrix Derivative Results for Forward and Reverse Mode Algorithmic Differentiation , 2008 .

[14]  Slobodan Ilic,et al.  PPFNet: Global Context Aware Local Features for Robust 3D Point Matching , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[15]  Fabio Remondino,et al.  A REVIEW OFPOINT CLOUDS SEGMENTATION AND CLASSIFICATION ALGORITHMS , 2017 .

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

[17]  M. Gross,et al.  Algebraic point set surfaces , 2007, SIGGRAPH 2007.

[18]  Chunhua Shen,et al.  Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Leonidas J. Guibas,et al.  Voronoi-Based Curvature and Feature Estimation from Point Clouds , 2011, IEEE Transactions on Visualization and Computer Graphics.

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

[21]  Jonathan Masci,et al.  Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Alexandre Boulch,et al.  Fast and Robust Normal Estimation for Point Clouds with Sharp Features , 2012, Comput. Graph. Forum.

[23]  Pierre Alliez,et al.  Eurographics Symposium on Geometry Processing (2007) Voronoi-based Variational Reconstruction of Unoriented Point Sets , 2022 .

[24]  Roland Siegwart,et al.  A Review of Point Cloud Registration Algorithms for Mobile Robotics , 2015, Found. Trends Robotics.

[25]  Leonidas J. Guibas,et al.  Estimating surface normals in noisy point cloud data , 2004, Int. J. Comput. Geom. Appl..

[26]  Maks Ovsjanikov,et al.  PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds , 2019, Comput. Graph. Forum.

[27]  Marc Pollefeys,et al.  Discriminatively Trained Dense Surface Normal Estimation , 2014, ECCV.

[28]  Heinrich Müller,et al.  SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[29]  Anath Fischer,et al.  Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds Using Convolutional Neural Networks , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[31]  Pierre Vandergheynst,et al.  Geodesic Convolutional Neural Networks on Riemannian Manifolds , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

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

[33]  Derek Hoiem,et al.  Indoor Segmentation and Support Inference from RGBD Images , 2012, ECCV.

[34]  Jan Eric Lenssen,et al.  Fast Graph Representation Learning with PyTorch Geometric , 2019, ArXiv.

[35]  David Levin,et al.  The approximation power of moving least-squares , 1998, Math. Comput..

[36]  Martin Buss,et al.  Comparison of surface normal estimation methods for range sensing applications , 2009, 2009 IEEE International Conference on Robotics and Automation.

[37]  Abhinav Gupta,et al.  Designing deep networks for surface normal estimation , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[38]  Alexandre Boulch,et al.  Deep Learning for Robust Normal Estimation in Unstructured Point Clouds , 2016, Comput. Graph. Forum.

[39]  Daniel Cohen-Or,et al.  Edge-aware point set resampling , 2013, ACM Trans. Graph..

[40]  Martial Hebert,et al.  Data-Driven 3D Primitives for Single Image Understanding , 2013, 2013 IEEE International Conference on Computer Vision.