sniklaus / 3d-ken-burns

an implementation of 3D Ken Burns Effect from a Single Image using PyTorch

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Meaning of parameters in meta data json files

waps101 opened this issue · comments

For the synthetic depth/normal dataset, there is a meta data json file included with the RGB images. This contains two parameters: intSample and fltFov. Could you explain what these mean? Ideally, I would like to be able to compute camera intrinsics in the form of focal length/principal point or a K matrix. Any guidance on doing this from the json files would be appreciated.

The intSample has little meaning outside the framework that I used to create the dataset. The reason why I included the meta file is the fltFov which is the field of view. You can derive the focal length from the field of view, the principal point is in the center, and the pinhole camera model is not subject to distortions. Please let me know in case there are any missing intrinsics.

I assume this is horizontal/vertical field of view as opposed to diagonal?

You are correct.

You may also find this interesting / useful: #37 (comment)