Appendix for "3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds " A Overview

B, we provide specific network architecture and more details about the target center parameterization for the voxel-to-BEV target localization network. As shown in Figure 1, we illustrate the specific network structure. Then, we present the 2D network to aggregate features in the BEV space. Finally, we provide more details on the target center parameterization. We also use a concatenated skip connection to fuse low-level and high-level features.