COLMAP reading bug

[Ramazan]

I get the following error while trying to train the model on custom COLMAP data:
CameraInfo.__new__() got an unexpected keyword argument 'image'

Apparently, you forgot to comment out passing an image argument when instantiating CameraInfo in readColmapCameras()

UPD:
Other arguments, such as background, timestep and camera_id are also missing:
TypeError: CameraInfo.__new__() missing 3 required positional arguments: 'bg', 'timestep', and 'camera_id'

UPD2:
Looks like interfaces have been changed, since SceneInfo is also missing arguments while working with COLMAP:
TypeError: SceneInfo.__new__() missing 5 required positional arguments: 'val_cameras', 'train_meshes', 'test_meshes', 'tgt_train_meshes', and 'tgt_test_meshes'

[Shenhan Qian]

Thanks for reporting the issues!

The data loading functions for COLMAP data are directly inherited from GaussianSpatting. They are outdated; thus, errors are expected.

You could update the interface for COLMAP data by mimicking our default interface for a "DynamicNerf" dataset.

[3Der1999]

Sorry to interrupt. Have you solved the problem？ @ramazan793

[Shenhan Qian]

We have added support for COLMAP datasets for static scenes via recent commits. You should be able to run datasets like MipNeRF360 within our code base. It should be easier to apply your custom datasets for head avatars then.