Sparse Convolutions on Continuous Domains for Point Cloud and Event Stream Networks
This work provides a more efficient and mathematically consistent convolution operator for researchers and practitioners working with sparse, unstructured continuous data, addressing the bottleneck of slow training and high memory usage.
The paper introduces a sparse matrix-based convolution operator for unstructured continuous data like point clouds and event streams. This method enables networks to train an order of magnitude faster on point cloud classification with comparable accuracy and significantly less memory, and achieves state-of-the-art results on event stream processing tasks.
Image convolutions have been a cornerstone of a great number of deep learning advances in computer vision. The research community is yet to settle on an equivalent operator for sparse, unstructured continuous data like point clouds and event streams however. We present an elegant sparse matrix-based interpretation of the convolution operator for these cases, which is consistent with the mathematical definition of convolution and efficient during training. On benchmark point cloud classification problems we demonstrate networks built with these operations can train an order of magnitude or more faster than top existing methods, whilst maintaining comparable accuracy and requiring a tiny fraction of the memory. We also apply our operator to event stream processing, achieving state-of-the-art results on multiple tasks with streams of hundreds of thousands of events.