How to have just one mesh for the same object at different pose

[TommasoBendinelli]

Hello, First of all congrats for the tool, I have been used it extensively. You can checkout my branch "tommaso" where I have created few scripts for bypassing the meshlab step using open3d library.

Anyway I have a question regarding the following problem: I have recorded two video of the same object lying in different positions (once on one side, and the other time on the other side). I hence I have created two different meshes. And currently my naive implementation is to consider these two meshes as two separate entities. Do you know how could I merge them together (maybe through ICP?) and so that I have just one mesh?

[F2Wang]

Hi,

First of all, thank you for using this tool, if you added any features you think may be useful to other users, please feel free to submit a pull request.

As for merging 2 pointcloud together, while ICP may work, it will require a good initialization. I think the best bet is to use meshlab to merge the 2 pointclouds together (It allows you to manually select matching points on 2 pointcloud respectively), resample the mesh, and performs surface reconstruction.

If you just want to get a complete mesh, the above method will do the trick. However, if you are using this tool for creating ground truth for 6D pose estimation projects, you will want the ground truth labels to be all regarding this one merged mesh. For example, if you aligned the 2nd mesh onto the first one, you will need to record this transformation and compose this transformation to all transforms originally computed on the 2nd sequence.

Thanks.