point cloud doesn't look that good about gradslam HOT 7 CLOSED

@nawara72
Sure thing! I can think of 2 likely reasons for the "fuzzy"ness:
1- Might want to play around with the point_size of the visualization (with open3d, you can change point size interactively with +/- shortcuts in the visualization; withplotly, you can specify point size by pointclouds.plotly(0, point_size=2))
2- In case of plotly visualization, we downsample the pointclouds before visualization because plotly visualization can be slow/break with large pointclouds.

You can use open3d for saving a pointcloud:

import open3d as o3d

o3d.io.write_point_cloud("pointcloud.ply", pointclouds.open3d(0))

from gradslam.

Great thanks for all your great support and help and will definitely share any output that I get from realsense
Thanks and take care

from gradslam.

Hi @nawara72,

Thanks for your interest! Would it be possible for you to share a sample output reconstruction so we can assist you better?

from gradslam.

Hi @nawara72,
The sequences argument for TUM expects something like:

dataset = TUM(basedir="C:/Users/cv/Documents/gradslam_data/TUM/", sequences=("rgbd_dataset_freiburg1_xyz", ), seqlen = 10)

where you specify a tuple of sequnce names which you want to load. I'm also curious if you can share a sample output reconstruction.
Here is a working example of PointFusion on TUM/rgbd_dataset_freiburg1_xyz in Google Colab:
https://colab.research.google.com/drive/1uxjEJI5B2yJJDG3SxoAagH9uEuT67rXC?usp=sharing

from gradslam.

Thanks for the quick reply and for sharing the TUM example code, really appreciate it. After running the code you shared, I got similar output to when I ran it. I just thought the output point cloud would be more sharper (ie not so fuzzy).
Is there any way I can write the pointcloud to a file (eg ply) to look at it in more detail.

Thanks and thanks again for all your efforts and for sharing

from gradslam.

Great will try that soon 👍
Also hoping soon to try and save some rgbd data from realsense and pass it to gradslam. Do you envisage any issues with that?
Thanks again

from gradslam.

Excited to see what that will look like! Can't envisage any issues at the moment, but if you find any bugs/unexpected behavior with the library or can think of extra features which would help your use case, feel free to open up another issue and we'll look into it!

from gradslam.