I am a second-year PhD student in the Imagine research group at École des Ponts ParisTech (ENPC) under the supervision of Mathieu Aubry. Before that, I received my engineering degree in mathematics and computer science from Mines ParisTech in 2019.
I am interested in computer vision, machine learning and deep learning. My research currently focuses on solving computer vision tasks without manual annotations, through automatically generated data, self-supervised learning techniques or unsupervised algorithms.
We characterize 3D shapes as affine transformations of linear families learned without supervision, and showcase its advantages on large shape collections.
An unsupervised learning framework to decompose images into object layers modeled as transformed instances of prototypical images called sprites.
Leveraging synthetic data and segmentation networks for generic element extraction in real historical document images.