isl-org
not all poses recovered
Hey, thanks for the great effort!
I am trying to evaluate my dense reconstruction pipeline. However, for some datasets of the advanced set I cannot successfully recover all camera poses neither with COLMAP of OpenMVG. I am actually missing 5 poses in the Palace set and 10 poses in the Auditorium.
My pipeline actually focuses on the dense reconstruction part, so I would need to start for some good poses, but I cannot recover them successfully with the available SfM pipelines.
Can I create the .log file anyway, so that I can upload and get the scores?
I actually think you should be fine, the way the evaluation works (or at least how I remember it), is that it does a robust matching of camera poses, to figure out scale and rough alignment. And it does an ICP refinement on the dense PC afterwards, so if you have a reasonably good looking dense result, you should be fine. Did you try to submit your results already?
@arknapit can you please point me to where in code it does the : "does a robust matching of camera poses, to figure out scale and rough alignment"? grateful,
it uses the Open3d registration function "registration_ransac_based_on_correspondence", which does not need the same amount of points (camera positions): https://github.com/isl-org/TanksAndTemples/blob/3c2c2125e9b16f32790c96a8953611de785d91d6/python_toolbox/evaluation/registration.py#L65 you check the README if you want to find an example of it working: python_toolbox/evaluation/README.md