Going Deeper with Lean Point Networks
This work addresses the challenge of efficient and scalable point cloud processing for computer vision applications, representing an incremental advancement.
The authors tackled the problem of training deeper and more accurate point processing networks by introducing Lean Point Networks (LPNs), which improved accuracy and memory consumption on multiple segmentation tasks.
In this work we introduce Lean Point Networks (LPNs) to train deeper and more accurate point processing networks by relying on three novel point processing blocks that improve memory consumption, inference time, and accuracy: a convolution-type block for point sets that blends neighborhood information in a memory-efficient manner; a crosslink block that efficiently shares information across low- and high-resolution processing branches; and a multiresolution point cloud processing block for faster diffusion of information. By combining these blocks, we design wider and deeper point-based architectures. We report systematic accuracy and memory consumption improvements on multiple publicly available segmentation tasks by using our generic modules as drop-in replacements for the blocks of multiple architectures (PointNet++, DGCNN, SpiderNet, PointCNN).