Closed jinzhiyang1 closed 2 years ago
Hi, you can use single image 6D pose estimation such as this , by skipping the hand state estimation. Or you can also use some 6D pose annotation tool to get the pose, e.g. https://github.com/sakizuki/6DPoseAnnotator.
Thanks for your reply, but I have a few more questions
How should I do that.
1)These are annotated ground truth pose for evaluation. In our case, we labeled frame by frame. For you own test data, if you don't need to evaluate, you can simply ignore these.
2)6d pose information of the whole model. For YCBInEOAT dataset, the models are YCB objects.
Hello, relying on your sharing, I made a new prediction data containing rgb map, depth map, with camera internal reference. But it lacks the annotated pose of the first frame, I would like to ask how can I get the pose of the first frame (4*4 matrix)