Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add script to jointly visualize GT and estimated scene #779

Merged
merged 15 commits into from
Mar 12, 2024

Conversation

johnwlambert
Copy link
Collaborator

No description provided.

senselessdev1 and others added 2 commits March 6, 2024 06:42
@ayushbaid
Copy link
Contributor

Can we not add GT as an optional arg in the current view_scene script?

@johnwlambert
Copy link
Collaborator Author

Can we not add GT as an optional arg in the current view_scene script?

Good idea, that's cleaner. Updated now


# Align the poses.
n = min(len(wTi_list), len(wTi_list_gt))
wTi_aligned_list, rSe = alignment_utils.align_poses_sim3_ignore_missing(wTi_list_gt[:n], wTi_list[:n])
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

How would this work if the missing cameras are towards the start of the sequence.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@ayushbaid good catch, fixed now

Comment on lines +78 to +79
for i in range(len(wTi_list_gt)):
wTi_list_gt[i] = zcwTw.compose(wTi_list_gt[i])
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why are we applying this transform to GT poses, but not the points?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Because I've set it up to only visualize GT poses, not GT points. Otherwise gets a bit too crowded in addition to the reconstructed points and reconstructed poses.

Copy link
Contributor

@ayushbaid ayushbaid left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@johnwlambert johnwlambert merged commit c095771 into master Mar 12, 2024
24 checks passed
@johnwlambert johnwlambert deleted the add-viz-vs-gt branch March 12, 2024 05:47
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants