-
Hi @XuyangBai
I'm sorry to disturb you with the following questions. In the process of 3dmatch training, in 9753 step
```
Steps desc_loss det_loss train_accuracy d_pos d_neg time memory
9753 n…
-
Thanks for share this amazing work. I want to try torch-points3d on registration tasks. However, I encounter some problems.
1. I encounter the transform errors in the ETHDataset and Kaist. [Log of …
-
Hello! Thank you for this repo, seems very interesting.
I'm trying to run your registration example, and I encoutered this error while loading the pretrained model:
`Error trying to create train…
-
Hi Xuyang,
I just noticed that you saved the aligned point cloud points as the training dataset but the testing dataset from 3DMatch are unaligned during the testing phase. May I confirm this with …
-
Hi Xuyang,
in one of the issues you have written that the receptiev field can be increased without increasing the voxel size. Could you elaborate shortly on that, do you just increase the conv_rad…
-
Sorry, i accidentally pressed 'Enter'. The following is the text.
Hi，Xuyang
Thanks for your sharing. I have run your code according to the README.md to test the 3DMatch dataset, but the results i …
-
Hi, Thanks for building such a useful library.
I try to run the notebook in `notebooks/demo_registration_3dm.ipynb`, but when I run to the line:
`model = PretainedRegistry.from_pretrained("minkow…
-
Many thanks to your relatively promising work. I would like to generate some training fragments from `3d match` dataset, and I found the statement in readme that `each pair of training fragments which…
-
Hello author,because of the network,I can't use your script files to download the dataset.So I download it from the 3DMatch(http://3dmatch.cs.princeton.edu/).However I noticed that the extract_data.py…
-
Hi, I would like to ask you about the tests you presented within the paper. In particular, I was trying to reproduce the results you obtained on 3DMatch using FGR. I am currently using the open3d libr…