Camera matching and background matching assist in compositing virtual 3D model into real background photo.

To calculate camera using perspective camera matching algorithm, pick corresponding 2D points on background image and 3D points on 3D model.
At least 5 point pairs are required (More Info). The 3D points cannot be in the same plane, and the 2D points cannot be on straight line. Practically you can't be sure that all points are appropriate and accurate, so it's a good idea to pick additional points.
After the point pairs are picked, click Compute to execute the algorithm. The outcome is a virtual camera that is in the approximate same virtual 3D location and orientation as the original real camera from which the photograph was shot.

Once the virtual camera has been computed to be in the same location and orientation as the real camera, you can render the 3D model on top of the photographed background image.

Tip: Background image, Final image and Preview window should have the same aspect ratio.

How do I collect calibration points?

Calibration for the model consists of the 3D (X,Y,Z) world coordinates of a feature point (in meters) and the corresponding coordinates (U,V) (in pixels) of the feature point in the image.
To pick 2D point press "2D" ("3D" off); To pick 3D point press "3D" ("2D" off); Press both to pick both 2D and 3D point (at the same click).

How many points are required for the algorithm?

The algorithm has two variants: one for coplanar data and one for non-coplanar data. For coplanar data the algorithm requires the z component of the 3D coordinates to be 0.
Basic coplanar calibration requires at least five data points. Basic non-coplanar calibration requires at least seven data points. Fully optimized calibration requires at least 11 data points for either coplanar and non-coplanar data.