search

WHU-USI3DV / CoFiI2P

[IEEE RA-L 2024] CoFiI2P: Coarse-to-Fine Correspondences-Based Image-to-Point Cloud Registration
https://whu-usi3dv.github.io/CoFiI2P/
56 stars 3 forks source link

How to set the threshold #4

Closed honghullw closed 1 month ago

honghullw commented 2 months ago

Hello！ May I ask if the threshold mentioned in your paper refers to setting it in the code? image image

kang-1-2-3 commented 2 months ago

These refers to point cloud augmentation, not the threshold for evaluate the test result.

honghullw commented 2 months ago

Thank you for your answer. So where should I set the threshold for evaluating test results in the code to achieve the effects described in the paper? image

kang-1-2-3 commented 2 months ago

You should use eval_all.py to load checkpoint and save test result. Then use calc_result.py to load test result, set threshold and evaluate the result with threshold.

honghullw commented 2 months ago

I understand, thank you very much for your answer.

martin-liao commented 1 month ago

Since the problem has been resolved, I will close the issue.