Jens Behley

Sorry for the very late reply. I'm not 100% sure, but these are simply the points after the first index in the `indices`, see https://github.com/PRBonn/lidar-bonnetal/blob/5a5f4b180117b08879ec97a3a05a3838bce6bb0f/train/common/laserscan.py#L152-L167 So if you want to...

sorry for the late reply. It's certainly possible to put the code into a ros node, but we currently have no plans to perform this. Regarding the performance on custom...

the links to the checkpoints are on the "README.md" of this repository:  If there is something missing, then let me know. (Or if I got your question wrong)

the problem with Qt seems not related to this issue, but I would try to reinstall the pyvis package as this seems to use Qt for visualization. Maybe there is...

I will have a look in the next days to replace the catkin-based setup with a proper cmake-only compile. I changed the way that glow is build now and that...

Short update on my efforts to make it cmake-buildable (similar to glow). Unfortunately, the TensorRT 5+ interface changed significantly, therefore, I have to dig into the TensorRT 8.x code of...

As the manual changes resolves this particular problem, I will now close this issue. I hopefully will look into getting rid of catkin with more modern tensor-rt in the future.

A bit late, but maybe it helps someone else. Sorry :/ The dynamic object removal is only implicitly happening by putting a penalty on the association in the computation of...

Not sure what you are referring to. Currently, I only support radius neighborhood searches. Not sure if this is the right data structure for the task that you are suggesting.

Here a possible things that you should check, such that we can rule out "easy problems": - Check if you have maybe a wrong `calib.txt` file (you cannot just copy...