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.

Sign up for GitHub

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

Jump to bottom

Compute First features, then matching #42

Merged
merged 7 commits into from
Jul 7, 2023
Merged

Compute First features, then matching #42

merged 7 commits into from
Jul 7, 2023

Conversation

danielsanjosepro
Copy link
Collaborator

@danielsanjosepro danielsanjosepro commented Jul 6, 2023 •
edited
Loading

Goal

Close 40, 39, 38

  • Compute features first of all the images
  • Create dense reconstruction with epipolar rectification
  • Recover from a wrongly computed E matrix

@danielsanjosepro danielsanjosepro self-assigned this Jul 6, 2023
@danielsanjosepro
Copy link
Collaborator Author

Delivery Area, two images, 27051 points. Some work on progress
image

@danielsanjosepro
Copy link
Collaborator Author

danielsanjosepro commented Jul 7, 2023 •
edited
Loading

Harder than I though. There is some kind of distortion with the images. My laptop cant handle these point clouds anyway ( 47398 points )
image

image

@lufixSch
Copy link
Collaborator

lufixSch commented Jul 7, 2023

How did you implement that this fast?

@lufixSch
Copy link
Collaborator

lufixSch commented Jul 7, 2023 •
edited
Loading

Harder than I though. There is some kind of distortion with the images. My laptop cant handle these point clouds anyway ( 47398 points )

Looks promising nevertheless. We could take a look at it with my Workstation. Maybe it can handle such a high number of points.
We still might have to implement some form of Filter to decide which features/pixels are interesting before reconstructing every single pixel.

@danielsanjosepro danielsanjosepro changed the title Dense reconstruction using Epipolar Rectification and Epipolar line search Compute First features, then matching Jul 7, 2023
@danielsanjosepro danielsanjosepro linked an issue Jul 7, 2023 that may be closed by this pull request
Precompute features of all the images and then the geometry dynamically #39
Closed
MariusGhica
MariusGhica approved these changes Jul 7, 2023
View reviewed changes
Copy link
Collaborator

@MariusGhica MariusGhica left a comment

Choose a reason for hiding this comment

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

LGTM

@MariusGhica MariusGhica merged commit c4f6d7c into main Jul 7, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@MariusGhica MariusGhica MariusGhica approved these changes

@lufixSch lufixSch Awaiting requested review from lufixSch

Assignees

@danielsanjosepro danielsanjosepro

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Precompute features of all the images and then the geometry dynamically
3 participants
@danielsanjosepro @lufixSch @MariusGhica