Open idhamari opened 4 months ago
Hello, I notice that your source and target models (the second sample) have a large translation difference. Since our code will first normalize the bounding box of the two models, the value may become very small and unstable. It is recommended that you translate the two models to a close position before trying again.
Thanks for sharing your code. I tried on a different dataset but it didn't work (please see the second sample in my pull request ). Any idea? Is there a specific preprocessing step one should do?
The aligned shape looks strange compared to the original:
Original
Result