Open szat opened 3 months ago
Hi, the "images_4" refers to the directory that contains images downsampled 4 times and it is provided in the mipnerf-360 dataset. When using your own dataset, you can tune the image factor using--data_factor
(e.g. --data_factor 1
is the original image size).
Hi, thx for the quick answer. Followup question, should colmap be run on the downsampled images, or run colmap on the original images and then downsample the images.
I think it's prefered to run colmap on the original images and then downsample the images. You also need to change the camera intrinsics when downsampling. Here's a reference for processing your own data in the oringinal 3DGS repo
Hi there, I was wondering if you could give a colmap dataset on which the examples/simple_training.py works, when I put my own colmap folder with the structure name/images, name/spares, it complains that name/images_4/ does not exist. Debugging now, but would be nice to have an example that just works.