-
Notifications
You must be signed in to change notification settings - Fork 38
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
A question about the result of 3DRegNet. #12
Comments
Hi, thanks for your interest. As shown in our paper (Supplementary 7.2) 3DRegNet does not work well on 3DMatch with their registration block so I only use the classification block to produce the inlier probability. Then 3DRegNet becomes a variant of PointCN (Learning to find good correspondence paper) which is the same as the following module (but you should uncomment the InstanceNorm first). I believe you can quickly derive a 3DRegNet model and use our implementation to train it by yourself. Lines 55 to 62 in b009d53
|
Thank you very much for your reply. I'd like to confirm again:
|
Yes, that setting is what I used during my experiment. |
And, I only use classified loss to train the network, i.e. BCE loss in pointDSC?
|
Hi, thank you very much for your well-organized pointDSC code. I noticed the experimental result of 3DRegNet on 3DMatch in your paper. Would you like to provide the code of 3DRegNet on 3DMatch? Thank you very much!
The text was updated successfully, but these errors were encountered: