PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

12/02/2016

∙

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.

READ FULL TEXT

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

RGCNN: Regularized Graph CNN for Point Cloud Segmentation

Point2Point : A Framework for Efficient Deep Learning on Hilbert sorted Point Clouds with applications in Spatio-Temporal Occupancy Prediction

PyramNet: Point Cloud Pyramid Attention Network and Graph Embedding Module for Classification and Segmentation

3DContextNet: K-d Tree Guided Hierarchical Learning of Point Clouds Using Local Contextual Cues

VV-Net: Voxel VAE Net with Group Convolutions for Point Cloud Segmentation

Geometric Algebra Attention Networks for Small Point Clouds

3D Point Cloud Feature Explanations Using Gradient-Based Methods

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

Related Research

RGCNN: Regularized Graph CNN for Point Cloud Segmentation

Point2Point : A Framework for Efficient Deep Learning on Hilbert sorted Point Clouds with applications in Spatio-Temporal Occupancy Prediction

PyramNet: Point Cloud Pyramid Attention Network and Graph Embedding Module for Classification and Segmentation

3DContextNet: K-d Tree Guided Hierarchical Learning of Point Clouds Using Local Contextual Cues

VV-Net: Voxel VAE Net with Group Convolutions for Point Cloud Segmentation

Geometric Algebra Attention Networks for Small Point Clouds

3D Point Cloud Feature Explanations Using Gradient-Based Methods