Supplementary Materials for " Every View Counts: Cross-View Consistency in 3D Object Detection with Hybrid-Cylindrical-Spherical Voxelization "

In this document we provide more details about implementation and experiments about different voxelization methods. For z we set 12 bins and range [ 5, 3]. We set 12 bins and range [ 3, 3] for log l, log, w, log h. We use code weight 0.5 for velocity prediction and 1.0 for other bounding box statistics. In the classification head, we set alpha=0.25, gamma=2.0 for Focal Loss [1].