Visualization and the usage of the ESDF map

[gogojjh]

Thanks for the great work!

I have tested the nvblox in my own computer and modified the code to support two features:

1. the mapping of using an Ouster-128 LiDAR
2. implementation of different weight averaging methods.
   If you are interested, I can pull a request. And please remind users that they should set specially -mesh_frame_subsampling=500 (for example) to avoid the memory issue for a large-scale dataset.

And I have a problem about the ESDF map. Could you please recommend any tools to visualize the ESDF map as shown in https://github.com/nvidia-isaac/nvblox/blob/public/docs/images/nvblox_slice.gif?
Thanks.

[alexmillane]

Hi. Thanks for your interest in nvblox. Your results look really cool!

We're definitely interested in you contributing your sensor models.

Could you send me an email on [email protected]?

[alexmillane]

We're very happy to have your contribution. Looking forward to your pull-request :).

[ZiliangMiao]

I got the same problem, how to visualize the ESDF map as shown in https://github.com/nvidia-isaac/nvblox/blob/public/docs/images/nvblox_slice.gif, or could you please recommend any other viz tools?

[gogojjh]

I think that you can publish a series of point cloud (each point records the distance)

[ZiliangMiao]

I think that you can publish a series of point cloud (each point records the distance)

Thanks for reply. Btw, I just discovered that you have adapted nvblox to the KITTI dataset! I think it is possible to follow your version to adapt nuScenes and Waymo dataset (related to my previously opened issue 37: #37).

[gogojjh]

Sure, I have previously pulled several requests. You can check them to adapt other public datasets.

[ZiliangMiao]

Sure, I have previously pulled several requests. You can check them to adapt other public datasets.

Hi Dr. Jiao @gogojjh,

I have encountered some problems running your code. I think that you have transferred the KITTI-format data into 3dmatch-format, which includes "seq-xx" folders, "lidar-intrinsics.txt", "frame-xxxxxx.color.png", "frame-xxxxxx.depth.png" and "frame-xxxxxx.poses.txt" files. However, I cannot access the provided download link of your data (stored in NAS), and I cannot find the data-format transfer script either. Could you please provide your data-format transfer script, and a Google Drive or Onedrive download link of your processed KITTI data? Thanks a lot!

Best,
Ziliang

[gogojjh]

Hi, I update the link again, please try:
FusionPortable dataset, 20220226_campus_road_day: http://gofile.me/72EEc/MDghPwECu
KITTI Sequence 07: http://gofile.me/72EEc/NGdCJrzA5
It may need time to enter the website.

The data-format transfer script is here:
function-savekittito_Nvbloxformat.txt

[ZiliangMiao]

Hi, I update the link again, please try: FusionPortable dataset, 20220226_campus_road_day: http://gofile.me/72EEc/MDghPwECu KITTI Sequence 07: http://gofile.me/72EEc/NGdCJrzA5 It may need time to enter the website.

The data-format transfer script is here: function-savekittito_Nvbloxformat.txt

Thanks a lot!