Open
Conversation
Collaborator
There was a problem hiding this comment.
is this an update to the base lightglue repo? is it needed in this PR?
Collaborator
Author
There was a problem hiding this comment.
I'm not really sure what's happening here. I deleted and reinitialized the submodule using git submodule update --init --recursive, and it's still recording a couple small changes.
Collaborator
There was a problem hiding this comment.
we dont specify a commit in gtsfm, so its using 746fac2 which is the latest (from 6 months ago), and it looks like this PR is moving it to a earlier commit, which is from 2024. So not a good idea to proceed with that. Could you check your lightglue branch and make sure its up to date with their origin/main?
dellaert
approved these changes
Jan 16, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Fixed multistage BA such that it uses the intermediate result to initialize the next step. I also consolidated
run_baand_run_ba_and_evalulatesince they were doing the same thing except that the latter computed metrics after each step (which is now controlled by a flag).I wonder if we really need multistage BA for 2-view pose estimation, or if using one stage gives similar performance while significantly reducing runtime (I believe 2-view estimation is our most time consuming step)? This change will likely already speed things up since we're not just running the same BA with different thresholds now.