PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessarily voluminous and causes issues. In this paper, we design a novel type of neural network that directly consumes point clouds and well respects the permutation invariance of points in the input. Our network, named PointNet, provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Though simple, PointNet is highly efficient and effective. Empirically, it shows strong performance on par or even better than state of the art. Theoretically, we provide analysis towards understanding of what the network has learnt and why the network is robust with respect to input perturbation and corruption.

References in zbMATH (referenced in 46 articles )

Showing results 1 to 20 of 46.
Sorted by year (citations)

1 2 3 next

  1. Jin, Pengfei; Lai, Tianhao; Lai, Rongjie; Dong, Bin: NPTC-net: narrow-band parallel transport convolutional neural networks on point clouds (2022)
  2. Wald, Johanna; Navab, Nassir; Tombari, Federico: Learning 3D semantic scene graphs with instance embeddings (2022)
  3. Yarotsky, Dmitry: Universal approximations of invariant maps by neural networks (2022)
  4. Gao, W., Nan, L., Boom, B., Ledoux, H.: SUM: A benchmark dataset of Semantic Urban Meshes (2021) not zbMATH
  5. Ghadai, Sambit; Lee, Xian Yeow; Balu, Aditya; Sarkar, Soumik; Krishnamurthy, Adarsh: Multi-resolution 3D CNN for learning multi-scale spatial features in CAD models (2021)
  6. Guo, Rui; Zhou, Yong; Zhao, Jiaqi; Yao, Rui; Liu, Bing; Zhang, Xunhui: Unsupervised spatial-awareness attention-based and multi-scale domain adaption network for point cloud classification (2021)
  7. Hua, Michelle; Gao, Mingqi; Zhong, Zichun: SCN: dilated silhouette convolutional network for video action recognition (2021)
  8. Jurewicz, Mateusz; Derczynski, Leon: Set-to-sequence methods in machine learning: a review (2021)
  9. Ma, Jiayi; Jiang, Xingyu; Fan, Aoxiang; Jiang, Junjun; Yan, Junchi: Image matching from handcrafted to deep features: a survey (2021)
  10. Ping, Yuhan; Wei, Guodong; Yang, Lei; Cui, Zhiming; Wang, Wenping: Self-attention implicit function networks for 3D dental data completion (2021)
  11. Wang, Guangyu; Xu, Gang; Wu, Qing; Wu, Xundong: Two-stage point cloud super resolution with local interpolation and readjustment via outer-product neural network (2021)
  12. Deng, Hao; To, Albert C.: Topology optimization based on deep representation learning (DRL) for compliance and stress-constrained design (2020)
  13. Eliasof, Moshe; Sharf, Andrei; Treister, Eran: Multimodal 3D shape reconstruction under calibration uncertainty using parametric level set methods (2020)
  14. Hackel, Timo; Usvyatsov, Mikhail; Galliani, Silvano; Wegner, Jan D.; Schindler, Konrad: Inference, learning and attention mechanisms that exploit and preserve sparsity in CNNs (2020)
  15. Hähnel, Philipp; Mareček, Jakub; Monteil, Julien; O’Donncha, Fearghal: Using deep learning to extend the range of air pollution monitoring and forecasting (2020)
  16. Lang, Xufeng; Sun, Zhengxing: Structure-aware shape correspondence network for 3D shape synthesis (2020)
  17. Liu, Li; Ouyang, Wanli; Wang, Xiaogang; Fieguth, Paul; Chen, Jie; Liu, Xinwang; Pietikäinen, Matti: Deep learning for generic object detection: a survey (2020)
  18. Liu, Xinhai; Han, Zhizhong; Hong, Fangzhou; Liu, Yu-Shen; Zwicker, Matthias: LRC-net: learning discriminative features on point clouds by encoding local region contexts (2020)
  19. Meta Platforms, Inc; Nikhila Ravi, Jeremy Reizenstein, David Novotny, Taylor Gordon, Wan-Yen Lo, Justin Johnson, Georgia Gkioxari: Accelerating 3D Deep Learning with PyTorch3D (2020) arXiv
  20. Nicolas Wagner, Ulrich Schwanecke: NeuralQAAD: An Efficient Differentiable Framework for High Resolution Point Cloud Compression (2020) arXiv

1 2 3 next