Implementation of bev_index, img_index

[ngoductuanlhp]

Hi, thank you for your great work.
I want to ask for the functions of bev_index, img_index in your PIXOR implementation (

pseudo-LiDAR_e2e/PIXOR/data/kitti_loader_lidar.py

Line 95 in 7392635

bev_index, img_index = fusion.Fusion(depth_map, calib, shift)

). I saw that you use these bev_index, img_index to map the image feature and point cloud feature in the forward() of PixorNet_Fusion. However, these variables are generated by the groundtruth depth map, even in the evaluation. I have regenerated these variables using the estimated depth map and the 3D detection performance is quite low. Could you check and illustrate this problem?