PointCNN: Convolution On X-Transformed Points. We present a simple and general framework for feature learning from point clouds. The key to the success of CNNs is the convolution operator that is capable of leveraging spatially-local correlation in data represented densely in grids (e.g. images). However, point clouds are irregular and unordered, thus directly convolving kernels against features associated with the points, will result in desertion of shape information and variance to point ordering. To address these problems, we propose to learn an X-transformation from the input points, to simultaneously promote two causes. The first is the weighting of the input features associated with the points, and the second is the permutation of the points into a latent and potentially canonical order. Element-wise product and sum operations of the typical convolution operator are subsequently applied on the X-transformed features. The proposed method is a generalization of typical CNNs to feature learning from point clouds, thus we call it PointCNN. Experiments show that PointCNN achieves on par or better performance than state-of-the-art methods on multiple challenging benchmark datasets and tasks.
Keywords for this software
References in zbMATH (referenced in 6 articles )
Showing results 1 to 6 of 6.
- 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)
- 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)
- Qian Xie, Yu-Kun Lai, Jing Wu, Zhoutao Wang, Yiming Zhang, Kai Xu, Jun Wang: MLCVNet: Multi-Level Context VoteNet for 3D Object Detection (2020) arXiv
- Yang, Baorong; Yao, Junfeng; Wang, Bin; Hu, Jianwei; Pan, Yiling; Pan, Tianxiang; Wang, Wenping; Guo, Xiaohu: P2MAT-NET: learning medial axis transform from sparse point clouds (2020)
- Zhang, Li-na; Wang, Shi-yao; Zhou, Jun; Liu, Jian; Zhu, Chun-gang: 3D grasp saliency analysis via deep shape correspondence (2020)
- Chen, Mingjia; Zou, Qianfang; Wang, Changbo; Liu, Ligang: EdgeNet: deep metric learning for 3D shapes (2019)