Using COLMAP camera models in Deep Image Matching

[GAMHer]

Dear @lcmrl

First of all, I want to express my gratitude for the fantastic work you've been doing!

I am trying to use classical COLMAP camera models in Deep Image Matching. For instance i'm trying to use a fish-eye camera model.

Whenever I try any of the following models

SIMPLE_RADIAL_FISHEYE, RADIAL_FISHEYE, OPENCV_FISHEYE, FOV, THIN_PRISM_FISHEYE

The error message I receive is: RuntimeError: Invalid camera model RADIAL_FISHEYE. This suggests that the camera model I'm trying to use is not recognized by Deep Image Matching.

I've tried to change upper case with lower case and use the dash "-" instead of the underscore "_," but the error persists.

Could you please help me pass to Deep Image Matching the correct instruction?

Your guidance on this matter would be invaluable and greatly appreciated.

[lcmrl]

Hi sorry for the late response. DIM does not use the camera model to match features, so you can use another camera model, then when you import it in COLMAP you can change the camera model to OPENCV_FISHEYE for the incremental reconstruction. Did you try to visualize the matches to see if they are reasonable?