Could you please provide your code for monocular 3D object detection?

[hold on]

Or could your provide me some tips?

[Xinlong Wang]

@kaixinbear The det part can be referred to the AVOD and F-PointNet repos. The key is to generate the pseudo lidar using the mono depth estimation model and organize the dataset part according to their instructions.

[hold on]

Thanks for your reply.I have another question: As the picture in your paper shows, your system decodes bg pixels and fg pixels seperately.But I can't find the code describe this process,could you please tell me where is the code for this procedure?