PointCNN: Convolution On $\mathcal{X}$-Transformed Points

We present a simple and general framework for feature learning from point clouds. The key to the success of CNNs is the convolution operator that is capable of leveraging spatially-local correlation in data represented densely in grids (e.g. images)... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
3D Instance Segmentation S3DIS PointCNN mIoU 65.39% # 1
mAcc 75.61 # 2
3D Point Cloud Classification ScanObjectNN PointCNN Overall Accuracy 78.5 # 4
3D Part Segmentation ShapeNet-Part PointCNN Class Average IoU 84.6 # 5
Instance Average IoU 86.14 # 16

Methods used in the Paper


METHOD TYPE
Convolution
Convolutions