Mathias Gehrig

Hi @DogggLee Q: **For example, rosbag in zurich_city_03 has 544 PointCloud messages, but in training sequence 'zurich_city_03_a', there are only 442 disparity maps here** A: I uploaded the raw rosbags...

Before going into more depth: You cannot get drift-free trajectories from Lidar+IMU. Are you also planning to somehow take gps data into account? I just want to make sure that...

Ok, I see. I never enforced that the disparity maps and lidar scans have the same timestamps. To give some context, the goal was to get disparity maps for frame...

"I need to interpolate the pose of each camera-frame by their timestamps when they are captured to generate the camera trajectory of each train sequence" A: **Yes**, if you want...

These are the files I used for Lio-mapping: https://drive.google.com/file/d/1ERpXIO5EFbVLCk5LzMjLEPPUsQf57Bpo/view?usp=sharing If I remember correctly I have adapted it sometimes a bit to get better results but it should be a decent...

HI @hkx123 Thank you for your interest. I think DSEC is not the right dataset for place recognition because we excluded overlapping sequences to avoid visual redundancy. Just in case,...

Hi @k-chaney Thanks for your contribution! Could you tell me more about those issues: 1. How should this script be used for people having similar issues with pip? Just modify...

Very interesting, thanks. I think then that it would make sense that I adapt the documentation for the pip installation. In case of the code, I believe that it is...

We only compute optical flow groundtruth for parts of the dataset without moving objects. Therefore we had to exclude some sequences because they contain moving objects. In this work, we...

Hi @boomboomluo We are planning to release the training code as part of an extension of this work but is unfortunately still a work in progress. In the meantime, is...