Questions on implementation details about h3dnet HOT 4 CLOSED

Thanks for your interests in our work!

Here are my answers to the questions:

1. For the first question, the best way to choose the threshold is to visualize the label with a couple of scenes and then decide on the threshold. The general rule of thumb is that you want to include labels as dense as possible while not overlapping with too many points in other surfaces or edges.
2. For the second question, we tried to eliminate it and we did not observe too much performance decrease.
3. Yes. It will. It does not affect the performance much as long as you have dense labels in each surface. Even if for same faces, let's say right and front, there are some in-balanced distribution in the labels. It still does not affect the performance much if you have dense labels for some face.

Hope this answers your question!

from h3dnet.

Thanks for your reply.

I have another question: how are the l_f, l_c, l_o in Eq 2 implemented in the code (ie, loss_helper.py)?
What do objectness_loss_opt and potential_loss mean?

Besides, there seems several errors in the code. Please confirm:

1. H3DNet/models/proposal_module_refine.py

   Line 82 in e89d092

   sem_cls_scores = net_transposed[:,:,start+3+num_heading_bin*2:start+3+num_heading_bin*2+num_size_cluster] # Bxnum_proposalx10

   I think it should be [:,:,start+3+num_heading_bin*2+num_size_cluster*4:]. PS: I don't understand why u use if-else when decoding size and class (ie, L68-87), the code inside the two conditions are the same.
2. If I didn't understand wrongly, in these two pieces of code:

   H3DNet/models/loss_helper.py

   Line 356 in e89d092

   pred_heading_class = torch.argmax(end_points['heading_scores'+'center'].detach(), -1) # B,num_proposal

   H3DNet/models/loss_helper.py

   Line 373 in e89d092

   pred_size_class = torch.argmax(end_points['size_scores'+'center'].contiguous(), -1).detach()

   'center' should be mode.

from h3dnet.

l_f is implemented in here, l_c is implemented in here and it was called here and the majority of l_o is implemented in here.

For the errors:

1. This is actually a small trick. I found out that optimizing the semantic label on the box type works slightly better. You can change it to semantic label (what you suggested). I think it should not make much difference. From L68-79, I think you can remove the if-else. I did not fully optimize the code.
2. For heading and size, we are only refining the angle offset or box size offset. It we are also changing the semantic type, then it will choose a different starting angle or a starting box size each time with optimization. Then, it will cause the angle offset and box size offset refinement unstable.

from h3dnet.

Got it. Thanks a lot.

from h3dnet.