GridNet: efficiently learning deep hierarchical representation for 3D point cloud understanding

Abstract

In this paper, we propose a novel and effective approach, namely GridNet, to hierarchically learn deep representation of 3D point clouds. It incorporates the ability of regular holistic description and fast data processing in a single framework, which is able to abstract powerful features progressively in an efficient way.Moreover, to capture more accurate internal geometry attributes, anchors are inferred within local neighborhoods, in contrast to the fixed or the sampled ones used in existing methods, and the learned features are thus more representative and discriminative to local point distribution. GridNet delivers very competitive results compared with the state of the art methods in both the object classification and segmentation tasks.

Keywords

3D point clouds / deep representations

References

[1] Maturana D, Scherer S. Voxnet: a 3D convolutional neural network for real-time object recognition. In: Proceedings of the IEEE International Conference on Intelligent Robots and Systems. 2015, 922–928

[2] Brock A, Lim T, Ritchie J,Weston N. Generative and discriminative voxel modeling with convolutional neural networks. In: Proceedings of Neural Information Processing Conference: 3D Deep Learning. 2016

[3] Hegde V, Zadeh R. Fusionnet: 3D object classification using multiple data representations. 2016, arXiv preprint arXiv:1607.05695

[4] Su H,Maji S, Kalogerakis E, Learned-Miller E.Multi-view convolutional neural networks for 3D shape recognition. In: Proceedings of the IEEE International Conference on Computer Vision. 2015, 945–953

[5] Yu T, Meng J, Yuan J. Multi-view harmonized bilinear network for 3D object recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018, 186–194

[6] Feng Y,Zhang Z, Zhao X, Ji R, Gao Y.GVCNN: group-view convolutional neural networks for 3D shape recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018, 264–272

[7] Qi C, Su H, Nießner M, Dai A, Yan M, Guibas L. Volumetric and multiview cnns for object classification on 3D data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, 5648–5656

[8] Kanezaki A, Matsushita Y, Nishida Y. Rotationnet: joint object categorization and pose estimation using multiviews from unsupervised viewpoints. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition. 2018, 5010–5019

[9] Zhou Y, Tuzel O. Voxelnet: end-to-end learning for point cloud based 3D object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018, 4490–4499

[10] Li Y, Bu R,Sun M, Chen B. Pointcnn: convolution on χ-transformed points. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems. 2018, 828–838

[11] Qi C, Su H, Mo K, Guibas L. Pointnet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017, 77–85

[12] Le T, Duan Y. Pointgrid: a deep network for 3D shape understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018, 9204–9214

[13] Ye X, Li J, Huang H, Du L, Zhang X. 3D recurrent neural networks with context fusion for point cloud semantic segmentation. In: Proceedings of European Conference on Computer Vision. 2018, 415–430

[14] Qi C,Yi L, Su H, Guibas L. Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017, 5099–5108

[15] Wu Z, Song S, Khosla A, Yu F,Zhang L, Tang X, Xiao J. 3D shapenets: a deep representation for volumetric shapes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015, 1912–1920

[16] Yi L, Kim V, Ceylan D, Shen I,Yan M, Su H, Lu C, Huang Q, Alla Sheffer, Leonidas Guibas, A scalable active framework for region annotation in 3D shape collections. ACM Transactions on Graphics, 2016, 35(6): 1–12

[17] Rethage D, Wald J, Sturm J, Navab N, Tombari F. Fully-convolutional point networks for large-scale point clouds. In: Proceedings of European Conference on Computer Vision. 2018, 625–640

[18] Liu Z, Tang H, Lin Y, Han S. Point-voxel CNN for efficient 3D deep learning. In: Proceedings of Annual Conference on Neural Information Processing Systems. 2019, 963–973

[19] Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014, 1–9

[20] He K, Zhang X, Ren S, Sun J.Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, 770–778

[21] Klokov R, Lempitsky V. Escape from cells: deep KD-networks for the recognition of 3D point cloud models. In: Proceedings of the IEEE International Conference on Computer Vision. 2017, 863–872

[22] Wang P, Liu Y,Guo Y,Sun C, Tong X.O-CNN: octree-based convolutional neural networks for 3D shape analysis. ACM Transactions on Graphics, 2017, 36(4): 1–11

[23] Tatarchenko M, Dosovitskiy A, Brox T. Octree generating networks: efficient convolutional architectures for high-resolution 3D outputs. In: Proceedings of the IEEE International Conference on Computer Vision. 2017, 2107–2115

[24] Riegler G, Ulusoy A, Geiger A. Octnet: learning deep 3D representations at high resolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017, 6620–6629

[25] Yi L, Su H, Guo X, Guibas L. Syncspeccnn: synchronized spectral CNN for 3D shape segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017, 6584–6592

[26] Zhi S, Liu Y, Li X, Guo Y. Lightnet: a lightweight 3D convolutional neural network for real-time 3D object recognition. In: Proceedings of the Workshop on 3D Object Retrieval. 2017, 9–16

[27] Li Y, Pirk S, Su H, Qi C, Guibas L. FPNN: field probing neural networks for 3D data. In: Proceedings of the 30th International Conference on Neural Information Processing Systems. 2016, 307–315

[28] Shen Y,Feng C, Yang Y, Tian D. Mining point cloud local structures by kernel correlation and graph pooling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018, 4548–4557

[29] Yang Y, Feng C, Shen Y, Tian D. Foldingnet: point cloud auto-encoder via deep grid deformation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018, 206–215

[30] Hua B, Tran M, Yeung S. Pointwise convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018, 984–993

[31] You H, Feng Y, Ji R, Gao Y. PVNet: a joint convolutional network of point cloud and multi-view for 3D shape recognition. In: Proceedings of the 26th ACM International Conference on Multimedia. 2018, 1310–1318

[32] Jiang M, Wu Y, Lu C. Pointsift: a sift-like network module for 3D point cloud semantic segmentation. 2018, arXiv preprint arXiv:1807.00652

[33] Li J, Chen B, Lee G. So-net: self-organizing network for point cloud analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018, 9397–9406

[34] Lecun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 1998, 86(11): 2278–2324

RIGHTS & PERMISSIONS

2021 Higher Education Press