TADNet: A Time and Attention-Based Point Cloud Denoising Network for Autonomous Driving in Adverse Weather

Abstract. Lidar technology is widely used in the field of autonomous driving by virtue of its high precision. However, under special weather conditions such as rain, snow, fog, etc., suspended particles in the air can contaminate the point cloud data collected by LIDAR, which leads to a significant performance degradation of the vehicle sensing system and increases the driving safety risk. To address this problem, we propose A Time and Attention-Based Point Cloud Denoising Network for Autonomous Driving in Adverse Weather (TADNet). The method is based on the 3D-OutDet network with the addition of Convolutional Block Attention Module (CBAM), which highlights important features and suppresses minor ones. The original ResNet base network architecture is changed to Temporal-Bottleneck ResNet (TB-ResNet) to improve the network's ability to recognize rain, snow and fog noise. We conducted comparative experiments between the TADNet method proposed in this paper and the filter-based point cloud denoising method and the deep learning-based point cloud denoising method. The experimental results show that the denoising effect of TADNet in three kinds of bad weather, namely rain, snow and fog, is better than other methods, which can remove different kinds of noise with different intensities and retain the environmental features, and has the best performance of IoU and MIoU in all kinds of weather conditions.