Akshay Krishnan

Have not looked at code, but just from your description, the ground truth scene and the computed scene are actually not the same reconstruction, so would it be better if...

We could maybe put all GT members in a different GtsfmData or maybe have another container GTSfMGTData, curious what @ayushbaid thinks

This requires the reference metrics to be stored on `master`. We can commit the artifacts we produce into the PR before merging. BUT the tricky issue here is that the...

An alternative is to run the metrics generation every night on `master` and make a commit directly to `master` (if and only if the commit on `master` does not change...

It’s not over there, but isn’t that necessary for the comparison? Just putting my thoughts here, this is probably not an urgent issue

Some of my thoughts: The metrics are the same for a type of module irrespective of the implementation. Ex: all translation averaging methods would have the same metrics. So we...

It is expected to have a high inlier ratio for the GT model (if the matcher output is good), but I don't understand why the inlier ratio with respect to...

Initial directions to investigate: - Force tracks to have minimum length 3 - Remove only outliers from the track after triangulation. - Try creating more tracks from outliers and merging...