PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Raffaelli Charles, Hao Su, Kaichun Mo et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2017
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, which 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.
Cited by 9,237 works. doi:10.1109/cvpr.2017.16
Authors
References
- Using spin images for efficient object recognition in cluttered 3D scenes
- 3D ShapeNets: A deep representation for volumetric shapes
- Fast Point Feature Histograms (FPFH) for 3D registration
- VoxNet: A 3D Convolutional Neural Network for real-time object recognition
- Multi-view Convolutional Neural Networks for 3D Shape Recognition
- Spectral Networks and Locally Connected Networks on Graphs
- Volumetric and Multi-view CNNs for Object Classification on 3D Data
- On Visual Similarity Based 3D Model Retrieval
- Rotation invariant spherical harmonic representation of 3D shape descriptors
- 3D Semantic Parsing of Large-Scale Indoor Spaces