SFL-NET: Slight Filter Learning Network for Point Cloud Semantic Segmentation

In recent years, point clouds have been widely used in power-line inspection, smart cities, autonomous driving, and other fields. Deep learning-based point cloud processing methods have achieved some impressive results in point cloud semantic segmentation, which has attracted more and more attention. However, there are still some problems that need to be solved, such as the efficiency of point cloud processing, inference speed, and parameter size of network. We mainly study how to remove the redundancy of neural network for large-scale point cloud semantic segmentation. Now that the scale of point cloud dataset has rapidly increased, many recent works adapt to it via expanding the model capacity, which can lead to a sharp decline in the efficiency and speed of processing point cloud. To address the problem, we propose an efficient and lightweight deep neural network, namely, slight filter learning network (SFL-Net), which can effectively extract semantic information and accelerate semantic segmentation for large-scale point clouds. The key to our approach is the proposed slight filter convolution (SFConv) module and the hourglass block (HB). SFConv is designed to remove the redundancy of 3-D convolution filters. HB can replace all multilayer perceptron (MLP) in the neural network to expedite point cloud processing. To reduce the information loss during the subspace transformation, we introduce a new correlation loss function to constrain the parameter pairs in HB. On public indoor and outdoor datasets evaluation, SFL-Net performance reaches and even outperforms the state-of-the-art (SOTA) approaches. Moreover, the model parameters of SFL-Net are reduced by
$10\times $
than the kernel point convolution (KPConv). The inference time of SFL-Net is only 45.8 s for about 100 million points (
${N}~\sim $
108).