Geometric Matrix Completion: A Functional View

Abhishek Sharma (1) , Maks Ovsjanikov (1)

1 LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau]

We propose a totally functional view of geometric matrix completion problem. Differently from existing work, we propose a novel regularization inspired from the functional map literature that is more interpretable and theoretically sound. On synthetic tasks with strong underlying geometric structure, our framework outperforms state of the art by a huge margin (two order of magnitude) demonstrating the potential of our approach. On real datasets, we achieve state-of-the-art results at a fraction of the computational effort of previous methods. Our code will be publicly available at \url{https://github.com/Not-IITian/functional_matrix_completion}

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Apprentissage [cs.LG]

Abhishek Sharma, Maks Ovsjanikov. Geometric Matrix Completion: A Functional View. 2020. ⟨hal-02871840v1⟩