Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models

ICCV 2017 Roman KlokovVictor Lempitsky

We present a new deep learning architecture (called Kd-network) that is designed for 3D model recognition tasks and works with unstructured point clouds. The new architecture performs multiplicative transformations and share parameters of these transformations according to the subdivisions of the point clouds imposed onto them by Kd-trees... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
3D Part Segmentation ShapeNet-Part Kd-net Class Average IoU 77.4 # 6
3D Part Segmentation ShapeNet-Part Kd-net Instance Average IoU 82.3 # 8