Pyramid Point: A Multilevel Focusing Network for Revisiting Feature Layers

We present a method to learn a diverse group of object categories from an unordered point set. We propose our Pyramid Point network, which uses a dense pyramid structure instead of the traditional “U” shape, typically seen in semantic segmentation networks. This pyramid structure gives a second look, allowing the network to revisit different layers created from various levels on the network, allowing for feature propagation. We introduce a focused kernel point convolution (FKP Conv), which expands on the traditional point convolutions by adding an attention mechanism to the kernel outputs. This FKP Conv increases our feature quality and allows us to weigh the kernel outputs dynamically. These FKP Convs are the central part of our Recurrent FKP Bottleneck block, which makes up the backbone of our encoder. With this distinct network, we demonstrate competitive performance on three benchmark datasets.