I have a data set of 3D images with some bounding box annotations. The images are too large to train something like YOLO 3D (would run out of memory), so I instead created slices of the 3D images with corresponding 2D bounding boxes and trained a 2D object detector. During inference, I assemble the 2D detections into 3D detections. I constructed some simple heuristics to do that, which works fine, but I am wondering if there aren't any established methods of doing that.
I appreciate if you could point me in the right direction.