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

ICCV 2017  ·  Roman Klokov, Victor 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. Unlike the currently dominant convolutional architectures that usually require rasterization on uniform two-dimensional or three-dimensional grids, Kd-networks do not rely on such grids in any way and therefore avoid poor scaling behaviour. In a series of experiments with popular shape recognition benchmarks, Kd-networks demonstrate competitive performance in a number of shape recognition tasks such as shape classification, shape retrieval and shape part segmentation.

PDF Abstract ICCV 2017 PDF ICCV 2017 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Point Cloud Classification ModelNet40 Kd-net Overall Accuracy 90.6 # 90
3D Point Cloud Classification ModelNet40 Kd-Net Overall Accuracy 91.8 # 85
3D Part Segmentation ShapeNet-Part Kd-net Class Average IoU 77.4 # 35
Instance Average IoU 82.3 # 59

Methods


No methods listed for this paper. Add relevant methods here