A method for training a first neural network to detect the viewpoint of an object visible on an image and belonging to a given category of object when this image is inputted to the first neural network, including: providing a dataset of pairs of images under different viewpoints, providing a second neural network configured to be able to deliver appearance information of an object, providing a third neural network configured to be able to deliver a synthetic image of an object of the category using appearance information and a viewpoint, jointly training the first neural network, the second neural network, and the third neural network.