PointConv: Deep Convolutional Networks on 3D Point Clouds

CVPR 2019 Wenxuan WuZhongang QiLi Fuxin

Unlike images which are represented in regular dense grids, 3D point clouds are irregular and unordered, hence applying convolution on them can be difficult. In this paper, we extend the dynamic filter to a new convolution operation, named PointConv... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Semantic Segmentation ScanNet PointConv 3DIoU 0.556 # 4
3D Part Segmentation ShapeNet-Part PointConv Class Average IoU 82.8 # 1
3D Part Segmentation ShapeNet-Part PointConv Instance Average IoU 85.7 # 2