Yi Wei

It indicates the batch size used for depth training.

The resolution 288x364 is same with the setting in CVD. In our extension work, we find that for most of scenes high resolution will bring higher performance. However, for a...

It means that we modify the original COLMAP and update some functions. When you "git clone --recursive [email protected]:weiyithu/NerfingMVS.git", you have already downloaded our version's COLMAP. However, what you download is...

Could you provide more details?

Yeah, it is out of memory.

It may because you used original COLMAP instead of our version's. You can refer to #15 and #2

Oh, that's great.

I also think it may be caused by GPU memory overflow. The resolution of your images are ?

How many picture names in train.txt ? The error comes from [https://github.com/weiyithu/NerfingMVS/blob/b7f6590be69611c814822dc32e2220857c4d1dbf/utils/pose_utils.py#L48](url). It is caused by the misalignment between image numbers in train.txt and images.bin.

The depth maps are only for evaluation. When you run your own data, you do not need them.