PointCNN is a simple and general framework for feature learning from point cloud, which refreshed five benchmark records in point cloud processing, including:

classification accuracy on ModelNet40 (91.7%) classification accuracy on ScanNet (77.9%) segmentation part averaged IoU on ShapeNet Parts (86.13%) segmentation mean IoU on S3DIS (62.74%) per voxel labelling accuracy on ScanNet (85.1%).


No comments to display.