In this paper we address the problem of visibility in position-based visual servoing. It is well known that the observed object may leave the field of view in such schemes, as there is usually no control in the image. Recent control schemes try to cope with this issue by defining an image-based constraint such that the object stays in the image. We propose to increase the convergence domain of such schemes by defining a new constraint that allows the observed object to leave partially the field of view. The general formulation is exposed and the computation of this constraint is detailed. Experiments show that controlling the visibility loss allows performing positionbased visual servoing tasks that were impossible to perform while keeping the whole object in the image.