PointGrid: A Deep Network for 3D Shape Understanding

CVPR 2018  ·  Truc Le, Ye Duan ·

This paper presents a new deep learning architecture called PointGrid that is designed for 3D model recognition from unorganized point clouds. The new architecture embeds the input point cloud into a 3D grid by a simple, yet effective, sampling strategy and directly learns transformations and features from their raw coordinates. The proposed method is an integration of point and grid, a hybrid model, that leverages the simplicity of grid-based approaches such as VoxelNet while avoid its information loss. PointGrid learns better global information compared with PointNet and is much simpler than PointNet++, Kd-Net, Oct-Net and O-CNN, yet provides comparable recognition accuracy. With experiments on popular shape recognition benchmarks, PointGrid demonstrates competitive performance over existing deep learning methods on both classification and segmentation.

PDF Abstract

Results from the Paper


Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
3D Point Cloud Classification ModelNet40 PointGrid Overall Accuracy 92.0 # 51
3D Part Segmentation ShapeNet-Part PointGrid Class Average IoU 82.2 # 21
Instance Average IoU 86.4 # 11

Methods