You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello @Viczyf, CLOCs can work with any pre-trained 3D and 2D detectors, so theoratically, if you have a better 3D/2D detector, you will have better performance. The new results of CLOCs on the kitti leaderboard is achieved by fusing the CT3D and cascade-RCNN, also with couple of small modifications, we will update the repo to include more better 3D detectors.
Thanks for your sharing.
I noticed that the CLOCs achieves much better performance on the official leaderboard than the number claimed in the paper. Can you please tell me how do you optimize the method or is there some bug?
http://www.cvlibs.net/datasets/kitti/eval_object.php?obj_benchmark=3d
@pangsu0613
The text was updated successfully, but these errors were encountered: