Is there a way of global alignment on GPU?

[halil-karabacak]

Checklist

• I have searched for similar issues.
• For Python issues, I have tested with the latest development wheel.
• I have checked the release documentation and the latest documentation (for main branch).

My Question

I have a simple tracking application and currently data projection association works fine for around 10FPS. But if I lost the tracking once or start from another view of the scanned object (scan already completeed but let's say I try to add some more scan on my completed data), than I need to apply a model to model alignment. I have seen there is a tensor Feature class merged, but haven't noticed any method that uses this implementation, like RANSAC cuda (idk if this possible). What do you recommend? Thanks.