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
You can check the _get_detected_objects() function to see how the detection boxes are constructed. The following is the result that I visualized.
The detection results are borrowed from BUTD-DETR. According to their description, they retrain the GroupFree detector with 485 categories on the ScanNet dataset.
How do you get the bboxes? Do the bboxes sizes are normalized? I can not visualize it in the ScanNetv2 dataset.
The text was updated successfully, but these errors were encountered: