3D Point Cloud Classification
120 papers with code • 5 benchmarks • 6 datasets
Image: Qi et al
By exploiting metric space distances, our network is able to learn local features with increasing contextual scales.
For example, on the challenging S3DIS dataset for large-scale semantic scene segmentation, the Point Transformer attains an mIoU of 70. 4% on Area 5, outperforming the strongest prior model by 3. 3 absolute percentage points and crossing the 70% mIoU threshold for the first time.
The perception models used in deep learning on the other hand are designed for individual modalities, often relying on domain-specific assumptions such as the local grid structures exploited by virtually all existing vision models.
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.
Deep neural networks on 3D point cloud data have been widely used in the real world, especially in safety-critical applications.
Specifically, the convolutional weight for local point set is forced to learn a high-level relation expression from predefined geometric priors, between a sampled point from this point set and the others.