Abstract: Images are synthesized from a source to a target nature through unsupervised machine learning (ML), based on an original training set of unaligned source and target images, by training a first ML architecture through an unsupervised first learning pipeline applied to the original set, to generate a first trained model and induced target images consisting in representations of original source images compliant with the target nature. A second ML architecture is trained through a supervised second learning pipeline applied to an induced training set of aligned image pairs, each including first and second items corresponding respectively to an original source image and the induced target image associated with the latter, to generate a second trained model enabling image syntheses from the source to the target nature. Also, applications to effective medical image translations.

Abstract: A method for generating a 3D image of a human body part including: train a generative network based on a library of human body part 3D scans of reference to obtain a generative model; make a 3D scan of a studied human body part; define a subset of the studied 3D scan by excluding the content of an area; optimize a latent variable for minimizing a distance between the defined subset and an image of a subset generated by the generative model from the latent variable; generate a complete 3D image of the studied human body part with the generative model using the optimized latent variable.

Abstract: Images are synthesized from a source to a target nature through unsupervised machine learning (ML), based on an original training set of unaligned source and target images, by training a first ML architecture through an unsupervised first learning pipeline applied to the original set, to generate a first trained model and induced target images consisting in representations of original source images compliant with the target nature. A second ML architecture is trained through a supervised second learning pipeline applied to an induced training set of aligned image pairs, each including first and second items corresponding respectively to an original source image and the induced target image associated with the latter, to generate a second trained model enabling image syntheses from the source to the target nature. Also, applications to effective medical image translations.