question about SDN fine-tune on KITTI

[Lin Bai]

All the codes mentioned below are from PointRCNN folder.

I noticed in 'kitti_dataset.py', dataloader reads depth ground truth from "KITTI/training/depth_map" folder. If I understand correctly, we can generate this folder by using the following command from Pseudo_Lidar_V2 repo.
python ./src/preprocess/generate_depth_map.py --data_path path-to-KITTI/ --split_file ./split/trainval.txt

I did so and displayed the file named "001596.npy". The result gives a sparse depth map (shown below). And I think this sparse depth map is used as ground truth to calculate the "Depth loss" in Figure 3.

In Section 4.2 Depth Estimation, you mentioned the pre-trained SDN is refined on KITTI dataset, do you just use similar sparse depth maps as ground truth to refine the SDN? And this means only about 3%-4% depth information is actually tuned?

[Rui Qian]

Please check Table 1 in paper for details.