Jens Behley

Results 108 comments of Jens Behley

No need to send me the files; I can access the submission via Codalab and I can have a look. I'm not sure what then goes wrong and have to...

I finally managed to look into the issue. Sorry that it took a bit longer. 1. I confirm: there seems to be a bug in the validator, but currently I...

yes, all values need to be divided by the image width/height, which is in our case 1024; thus your file should look something like this: ```csv 1 0.77832 0.105988 0.34668...

Please see the first page of the competition: ![Image](https://github.com/user-attachments/assets/b28df983-707c-4cc9-b781-e6ecb4168924) The new competition can be found at: https://codalab.lisn.upsaclay.fr/competitions/7170

There are multiple questions: 1. Scans with poses: The KITTI dataset has poses, but we are even using poses from our own SLAM pipeline (SuMa). The individual scans, like each...

That's by design to avoid overfitting on the test results as also described on the competition website. Ablations and hyperparameter tuning should be only conducted on the validation set as...

Just for reference, you should get for sequence 00 the following output: ![Image](https://github.com/user-attachments/assets/3b6d19d7-0061-471c-8ad3-963d90f8c20a) Can you check that the `velodyne` folder contains 4541 files, where each `.bin` file is approximately 2...

the "car points" are simply the eco vehicle points that are filtered while loading. Can you simply use the poses provided with our labels? I guess that it not be...

thanks for your interest in our work and the feedback. 1. Yes, I should have added it to the Readme; you call `./visualizer [] []`, where the path to data...

Regarding what KITTI did for the motion compensation only the authors know. I guess they used the IMU estimates. But cannot tell for sure.