Metric depth estimation for custom outdoor data

[ssuralcmu]

The model looks promising and I would like to use it for metric depth estimation from camera images from my own cameras, which have varying intrinsic and extrinsic parameters. Some could be zoomed-in or out. Since the model does not use any camera parameters as input, can it still be used out-of-the-box for my use case to get absolute depth information? Let me know the best approach for this.