Some questions about code details and abnormal phenomenon

[Impuuuuuu]

Hi, it's very kind of you for releasing the code of the paper, and there are some questions about code details and abnormal phenomenon:

As is shown in the first image, I am bit confused of the codes in 140-144 lines of ./data/dtu.py. The reference should be the first element of "view_ids", the in codes in 140-144 lines you have put in the last position. Is something wrong with my understanding?

And again in the codes in 233-234 lines of ./train_mvs_nerf_pl.py, here appears two notions, tgt and ref. So may I ask what exactly src, ref, and tgt stands for?

Is the "with_depth" option means that we have got the depth map of dataset and we should not activate it if we do not get the depth map?

Last qusetion, when I train with my own dataset, nan appears after a few iterations. Have you ever met with the same problem?

Looking forward to your answers. Thanks for your work again.

[apchenstu]

Hi, thanks, 1. we define the 'reference view' (mostly used in other papers) to be target view, so we put it at the last, and randomly select 3 views to the source views. 2. please refer to the figure of our pipeline, 3. that's right, 4. oh, I didn't train this model with other datasets, so I don't have much sense on this issue. I think you can try to overfitting on a single scene, I believe this can help you for debugging.

[Impuuuuuu]

Hi, thanks, 1. we define the 'reference view' (mostly used in other papers) to be target view, so we put it at the last, and randomly select 3 views to the source views. 2. please refer to the figure of our pipeline, 3. that's right, 4. oh, I didn't train this model with other datasets, so I don't have much sense on this issue. I think you can try to overfitting on a single scene, I believe this can help you for debugging.

Thanks for your reply quite a lot!