no code implementations • 10 Sep 2021 • Ivan Molodetskikh, Mikhail Erofeev, Andrey Moskalenko, Dmitry Vatolin
We propose a novel neural-network-based method to perform matting of videos depicting people that does not require additional user input such as trimaps.
1 code implementation • 27 Apr 2021 • Andrey Moskalenko, Mikhail Erofeev, Dmitriy Vatolin
In this article, we propose a method that solves the problem of inpainting arbitrary-size images.
no code implementations • 14 Jul 2019 • Ivan Molodetskikh, Mikhail Erofeev, Dmitry Vatolin
The field of automatic image inpainting has progressed rapidly in recent years, but no one has yet proposed a standard method of evaluating algorithms.
no code implementations • 19 Mar 2019 • Vitaliy Lyudvichenko, Mikhail Erofeev, Alexander Ploshkin, Dmitriy Vatolin
We propose a compression method that uses a saliency model to adaptively compress frame areas in accordance with their predicted saliency.