We propose a novel end-to-end deep scene flow model, called PointPWC-Net, that directly processes 3D point cloud scenes with large motions in a coarse-to-fine fashion.
Hence, we preserved the invariances from the point convolution operation whereas attention is used to select relevant points in the neighborhood for convolution.
This paper investigates different variants of PointConv, a convolution network on point clouds, to examine their robustness to input scale and rotation changes.
The recent introduction of Unified Virtual Memory (UVM) in GPUs offers a new programming model that allows GPUs and CPUs to share the same virtual memory space, shifts the complex memory management from programmers to GPU driver/ hardware, and enables kernel execution even when memory is oversubscribed.
We propose a novel end-to-end deep scene flow model, called PointPWC-Net, on 3D point clouds in a coarse-to-fine fashion.
In this paper, we propose a novel approach to visualize features important to the point cloud classifiers.
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 #2 on 3D Part Segmentation on IntrA