search

TRAILab / CaDDN

Categorical Depth Distribution Network for Monocular 3D Object Detection (CVPR 2021 Oral)
Apache License 2.0
359 stars 62 forks source link

Training on custom dataset #50

Closed chetanmreddy closed 2 years ago

chetanmreddy commented 3 years ago

Hello Thank you for your great work.

I am trying to train your model on a custom dataset where we have 3d bounding boxes for images. But we don't have depth maps or sparse LIDAR maps. Can I still use your model for 3d object detection on our dataset?

Thanks again for your help.

codyreading commented 3 years ago

Hi and thanks for the interest!

You can try to use CaDDN without the depth loss, but I would not expect great results. This was actually an ablation study I did for the paper, in Table 3, Exp.2, in which performance was about half without the depth loss.