As mentioned here #8 , there is no loader implemented currently to load data in a generic format. It would be good to support loading COLMAP models to enable people to run ViewFormer on video sequences.
Currently, if you want to write your own loader, it should be quite easy if you start from the 7Scenes loader.
As mentioned here #8 , there is no loader implemented currently to load data in a generic format. It would be good to support loading COLMAP models to enable people to run ViewFormer on video sequences.
Currently, if you want to write your own loader, it should be quite easy if you start from the 7Scenes loader.