We present a supervised approach to recover 3D models of buildings from multiple uncalibrated views. With this method the user matches 3D vertices in the images and defines the 3D model of the building with the help of elementary and intuitive geometric constraints. At the same time, a graph describing relationships between vertices is built. Then, unknown parameters of this graph are estimated non-linearly through a bundle adjustment to recover the building model and the camera parameters. This method asserts that geometric rules are perfectly respected. This approach is used to recover independently 3D parts of the building with suitable images. Then all these independent 3D models are merged to obtain a full multiscale model of the building. An example on real images is given.