Thank you for your work! I have been able to run the code on my custom data and obtain the 3D reconstruction of my object.
My question is, does your code-base allow for tracking the same object but in unseen images?
I've been studying the source code and, from what I gather, the 3D reconstruction is the main output of the code. The tracking of the object seems to be a by-product of the process for generating the final 3D model. As such, it doesn't seem like I can use the results and track the same object in a different scene.
Is this the case?
Please let me know if there is anything I may be missing.
Any comments/suggestions would be more than appreciated!