-
Hi, I am trying to train on scannet dateset with a voxel map as input, but I encounter an "out of bound" error when running build_octree function. I was wonder do you have any example how we should tr…
-
Hi!
Thanks for your great work. I tested with Scannet++ Dataset and its works well. I want to test your model with WoodScape dataset (not Colmap). Is that your model available for this dataset?
T…
-
Hi,
I have downloaded the pretrained model from model zoo from this link: http://kaldir.vc.in.tum.de/3dsis/contrastive_scene_contexts/pretrain/partition8_4096_100k.pth and trained the model for seman…
-
Hello, thanks for sharing your code! Recently I want to train bonet with scannet database, and I followesd the step in #6 to process scannet database, firstly I ran helper_data_scannet_prepare.py to g…
-
It is great work，i am trying use the subset of ScanNet frames to test.But it seems cant load,weather have solution to achieve rapid detection
-
Nice works , I want to inference on my own point cloud data? what data should I prepare? Thanks.
-
Thank you very much for sharing your well organized code. I have a question about ScanNet dataset. I noticed that there is "-1" in the label of the processed ScanNet training set. Is this part of the …
-
Hi,
Thank you for sharing your code!
Could you please also share the meshes generated by your method? similar to what you did for VoRTX ?
Thanks
-
Traceback (most recent call last):
File "project_feature.py", line 158, in
scene = torch.load(os.path.join(SCANNET_DATA, "train", scene_id)+".pth")["coord"]
File "/root/miniconda3/envs/par…
-
Hi, I would like to have further information about the Scannet dataset you used for the multiview experiments.
1. Do you have a list of frames used for the evaluation?
2. Are the settings for pair…