search

pclucas14 / lidar_generation

Code for "Deep Generative Models for LiDAR Data"
79 stars 20 forks source link

Regarding mayavi code for visulaizing Lidar in preprocessed from [2,40,256] format #18

Closed prashkmr closed 2 years ago

prashkmr commented 2 years ago

Dear Lucas,

Your visualizations are very impressive. I was using mayavi for visualizations for preprocessed LiDAR point cloud in the preprocessed format. Could you share the scripts you had used to visulaized the reconstructed [2,40,256] range image as a point cloud as seen in your paper. I would really love to us them. They look extra clear and crisp.

Requesting your help here.

-Prashant

pclucas14 commented 2 years ago

Hi Prashant,

To convert from polar representation to (x,y,z) space, you can use the methor from_polar or from_polar_np if you have a numpy array. You can find them here. Once that is done, you can visualize the point cloud using the mayavi package, as I do in the method show_pc which you can find here.

Once you have generated the images and saved them as separate files, You can look at cell [25] of this notebook

That's the general approach. Note that this is some pretty old code, so you may have to give it a bit of love to make it work.

Happy Holidays, Lucas