Torsten Sattler
From a single image, you cannot get the 3D position of the point the user is looking at. You can only get the 3D ray that will contain the point,...
You could scale the camera positions (computed as `-R^T * t` for each camera) using the known size and then use the `model_aligner` to scale the model. I don't think...
During the reconstruction, the coordinate system is initialized with the local coordinate system of the first image that gets reconstructed (which does not need to be the first image in...
The point_triangulator does not refine the camera poses during bundle adjustment. Only the 3D point positions are optimized (see https://github.com/colmap/colmap/blob/dev/src/exe/sfm.cc#L454-L457). If you observe wrong poses, then your input poses are...
Colmap does not support line features or line feature triangulation.
You will have to ask @ahojnnes , who is the developer of Colmap.
The scaling factor is random and comes from the fact that it is impossible to determine the size of the scene from 2D measurements alone if you do not know...
I am not sure what you mean by the scaling factor for the intrinsics. While it is impossible to recover the size of the scene from images, it is possible...
There is a single scaling factor.
> Can I just divide the camera to object distance with the same distance estimated by colmap to get the scaling factor? Yes. > Will the scaling factor be same...