First of all, thank you for your great paper and codes, and also the trained model you provided.
I trained the model on ModelNet40 using the default settings in your code twice. Then I found the performance on the evaluation set of my best model is much worse than the results in Table 1 in the paper.
The test was performed on the second half categories with 1000 points sampled. I also test your provided trained model with the same setting and got the same performance as in the paper:
I guess this proves that adding point sampling during testing doesn't harm the performance?
Therefore, I would like to know more details about how you train and test over ModelNet40:
Is the best model selected by total test loss or test transformation loss?
In the paper you mentioned that
We also partitioned 20% of the training set for evaluation.
Does it mean that you used 20% training + the whole test set for validation during training and testing? Or did you only use the 20% training set for training and testing?
Are there any additional settings for testing on ModelNet40? I see the code is for 3DMatch in default.
Hi,
First of all, thank you for your great paper and codes, and also the trained model you provided.
I trained the model on ModelNet40 using the default settings in your code twice. Then I found the performance on the evaluation set of my best model is much worse than the results in Table 1 in the paper.
The test was performed on the second half categories with 1000 points sampled. I also test your provided trained model with the same setting and got the same performance as in the paper:
I guess this proves that adding point sampling during testing doesn't harm the performance?
Therefore, I would like to know more details about how you train and test over ModelNet40:
Thanks again.