Learning Robust Graph-Convolutional Representations for Point Cloud Denoising

Point clouds are an increasingly relevant geometric data type but they are often corrupted by noise and affected by the presence of outliers. We propose a deep learning method that can simultaneously denoise a point cloud and remove outliers in a single model. The core of the proposed method is a graph-convolutional neural network able to efficiently deal with the irregular domain and the permutation invariance problem typical of point clouds. The network is fully-convolutional and can build complex hierarchies of features by dynamically constructing neighborhood graphs from similarity among the high-dimensional feature representations of the points. The proposed approach outperforms state-of-the-art denoising methods showing robust performance in the challenging setup of high noise levels and in presence of structured noise.

[1]  M. Gross,et al.  Algebraic point set surfaces , 2007, ACM Trans. Graph..

[2]  Nikos Komodakis,et al.  Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Cohen-OrDaniel,et al.  ℓ1-Sparse reconstruction of sharp point set surfaces , 2010 .

[4]  Olga Sorkine-Hornung,et al.  Point Cloud Noise and Outlier Removal for Image-Based 3D Reconstruction , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

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

[6]  Daniel Cohen-Or,et al.  Parameterization-free projection for geometry reconstruction , 2007, ACM Trans. Graph..

[7]  Thomas S. Huang,et al.  Non-Local Recurrent Network for Image Restoration , 2018, NeurIPS.

[8]  Wei Hu,et al.  Differentiable Manifold Reconstruction for Point Cloud Denoising , 2020, ACM Multimedia.

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

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

[11]  Joan Bruna,et al.  Deep Convolutional Networks on Graph-Structured Data , 2015, ArXiv.

[12]  Enrico Magli,et al.  Learning Localized Generative Models for 3D Point Clouds via Graph Convolution , 2018, ICLR.

[13]  Markus H. Gross,et al.  Feature Preserving Point Set Surfaces based on Non‐Linear Kernel Regression , 2009, Comput. Graph. Forum.

[14]  Alexander M. Bronstein,et al.  Deformable Shape Completion with Graph Convolutional Autoencoders , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[15]  Lei Zhang,et al.  Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising , 2016, IEEE Transactions on Image Processing.

[16]  Nico Blodow,et al.  Towards 3D Point cloud based object maps for household environments , 2008, Robotics Auton. Syst..

[17]  Lei Wang,et al.  Appendix for : Graph Attention Convolution for Point Cloud Semantic Segmentation , 2019 .

[18]  Alexey Castrodad,et al.  Point Cloud Denoising via Moving RPCA , 2017, Comput. Graph. Forum.

[19]  Wenping Wang,et al.  Denoising point sets via L0 minimization , 2015, Comput. Aided Geom. Des..

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

[21]  Stefan Harmeling,et al.  Image denoising: Can plain neural networks compete with BM3D? , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[22]  Yue Wang,et al.  Dynamic Graph CNN for Learning on Point Clouds , 2018, ACM Trans. Graph..

[23]  Lei Gao,et al.  Signal Processing: Image Communication , 2022 .

[24]  Timo Ropinski,et al.  Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[25]  Gene Cheung,et al.  3D Point Cloud Denoising via Bipartite Graph Approximation and Reweighted Graph Laplacian , 2018, 1812.07711.

[26]  Jure Leskovec,et al.  How Powerful are Graph Neural Networks? , 2018, ICLR.

[27]  Pascal Frossard,et al.  The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains , 2012, IEEE Signal Processing Magazine.

[28]  Pietro Liò,et al.  Principal Neighbourhood Aggregation for Graph Nets , 2020, NeurIPS.

[29]  Markus H. Gross,et al.  PointProNets: Consolidation of Point Clouds with Convolutional Neural Networks , 2018, Comput. Graph. Forum.

[30]  Enrico Magli,et al.  Deep Graph-Convolutional Image Denoising , 2019, IEEE Transactions on Image Processing.

[31]  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).

[32]  Alán Aspuru-Guzik,et al.  Convolutional Networks on Graphs for Learning Molecular Fingerprints , 2015, NIPS.

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

[34]  Gene Cheung,et al.  3D Point Cloud Denoising Using Graph Laplacian Regularization of a Low Dimensional Manifold Model , 2018, IEEE Transactions on Image Processing.

[35]  Pierre Vandergheynst,et al.  Graph-based denoising for time-varying point clouds , 2015, 2015 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON).

[36]  Robert T. Collins,et al.  A space-sweep approach to true multi-image matching , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[37]  Andreas Uhl,et al.  BlenSor: Blender Sensor Simulation Toolbox , 2011, ISVC.

[38]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[39]  Jelena Kovacevic,et al.  3D Point Cloud Denoising via Deep Neural Network Based Local Surface Estimation , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[40]  Paolo Cignoni,et al.  MeshLab: an Open-Source Mesh Processing Tool , 2008, Eurographics Italian Chapter Conference.

[41]  B. Frey,et al.  Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning , 2015, Nature Biotechnology.

[42]  Edmond Boyer,et al.  FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[43]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[44]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[45]  Enrico Magli,et al.  Learning Graph-Convolutional Representations for Point Cloud Denoising , 2020, ECCV.

[46]  Dong Tian,et al.  Geometric distortion metrics for point cloud compression , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[47]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[48]  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).

[49]  Marc Alexa,et al.  Computing and Rendering Point Set Surfaces , 2003, IEEE Trans. Vis. Comput. Graph..