Open hyqshr opened 1 week ago
My understanding is there's an additional layer of transformation between pose in transform.json
and pose actually used by nerfstudio while training. That transformation is applied in nerfstudio_dataparser.py:L236-249. In my understanding these lines does following to the original colmap camera pose.
camera_pose = transform@camera_pose
camera_pose[:3,3] *= scale_factor
The transformation matrix and scale factor can be found in dataparser_transforms.json
in the output folder. The applied_transform
field in transform.json
is not used I think.
For the same frame in a dataset:
Result from
transforms_train.json
(ns-export camera
)Result from colmap
transform.json
:Do
transforms_train.json
(fromns-export camera
) share the same coordinates withcamera_path.json
from splatfacto? What's the conversion from colmap to camera_path.json coordinates? Is there any scale difference?