How to apply the BEVFormer to the 3D OCC task？

[qiy20]

Thanks for your great work !
I am particularly interested in details about how to apply the 2D BEVFormer to the 3D OCC task？

[huang-yh]

We simply made predictions on 2D BEV feature map and assigned predictions to voxels according to their xy coordinates.
Though we did not go further than that, it should be better to apply some lightweight decoder on the 2D BEV feature map to diversify predictions along the z axis.