no code implementations • 30 May 2024 • Egor Kashkarov, Egor Chistov, Ivan Molodetskikh, Dmitriy Vatolin
Perceptual losses play an important role in constructing deep-neural-network-based methods by increasing the naturalness and realism of processed images and videos.
1 code implementation • 8 May 2023 • Evgeney Bogatyrev, Ivan Molodetskikh, Dmitriy Vatolin
We assessed 17 state-ofthe-art SR models using our benchmark and evaluated their ability to preserve scene context and their susceptibility to compression artifacts.
1 code implementation • 20 May 2022 • Viacheslav Meshchaninov, Ivan Molodetskikh, Dmitriy Vatolin
To explain how the method detects videos, we systematically review the major components of our framework - in particular, we show that most data-augmentation approaches hinder the learning of the method.
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.
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 • World of Technique of Cinema 2018 • Ivan Molodetskikh, Dmitriy Vatolin
Some movies are released in two or more versions.