limacv/Deblur-NeRF

Colmap preprocessing

Opened this issue · 3 comments

dogyoonlee commented

Hi

I wonder how to generate the camera pose for blurry inputs (e.g. blurcozy2room scene).

When I run the colmap with 34 images in blurcozy2room directory, error raise.

ERROR: the correct camera poses for current points cannot be accessed

However, when I run the same code for clean image set, it works.

I guess colmap seems to be having trouble getting it to work correctly.

Could you share how to generate the camera poses for blurry inputs?

Thank you !

limacv commented

We export the GT camera poses directly from the Blender file for the synthetic dataset (as is the cozyroom).

chenkang455 commented

We export the GT camera poses directly from the Blender file for the synthetic dataset (as is the cozyroom).

how about the real-blur dataset?

limacv commented

We extract from COLMAP (which is why it might be inaccurate and we don't use it for numerical evaluation)