33 papers with code • 1 benchmarks • 0 datasets
By exploiting metric space distances, our network is able to learn local features with increasing contextual scales.
Ranked #4 on Semantic Segmentation on ShapeNet
The proposed method is a generalization of typical CNNs to feature learning from point clouds, thus we call it PointCNN.
Ranked #1 on 3D Instance Segmentation on S3DIS (mIoU metric)
Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices.
Ranked #5 on 3D Point Cloud Classification on ScanObjectNN
Besides, our experiments converting CIFAR-10 into a point cloud showed that networks built on PointConv can match the performance of convolutional networks in 2D images of a similar structure.
Ranked #9 on Semantic Segmentation on ScanNet