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
In my understanding, the released code is the offline implementation, since the virtual point is preprocessed before the model is trained and tested.
I am curious about whether an online implementation has been tried, where the virtual point is added to the original point cloud in the process of training and testing?
Thanks in advance.
The text was updated successfully, but these errors were encountered:
thank you for the interest! We didn't try this back then.
To get an online version, I think we basically need to chain a few scripts (2d detection, point generation, and 3d detection). For 2d part, the detector is fast but image reading / resizing / processing needs some optimization. For point generation, we need some works to remove those few for loops.
Hi, thanks for your excellent work.
In my understanding, the released code is the offline implementation, since the virtual point is preprocessed before the model is trained and tested.
I am curious about whether an online implementation has been tried, where the virtual point is added to the original point cloud in the process of training and testing?
Thanks in advance.
The text was updated successfully, but these errors were encountered: