PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

CVPR 2017 Charles R. QiHao SuKaichun MoLeonidas J. Guibas

Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images... (read more)

PDF Abstract

Code


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Skeleton Based Action Recognition CAD-120 PointNet (5-shot) Accuracy 69.1% # 7
3D Point Cloud Classification ModelNet40 PointNet [qi2017pointnet] Overall Accuracy 89.2 # 7
Mean Accuracy 86.0 # 3
Scene Segmentation ScanNet PointNet++ Average Accuracy 60.2% # 2
3D Semantic Segmentation SemanticKITTI PointNet mIoU 14.6% # 15
3D Part Segmentation ShapeNet-Part PointNet Class Average IoU 80.4 # 10
Instance Average IoU 83.7 # 13

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet