1 code implementation • 27 Apr 2024 • Diana Sungatullina, Tomas Pajdla
We present an approach to backpropagating through minimal problem solvers in end-to-end neural network training.
no code implementations • ECCV 2018 • Diana Sungatullina, Egor Zakharov, Dmitry Ulyanov, Victor Lempitsky
The new architecture, that we call a perceptual discriminator, embeds the convolutional parts of a pre-trained deep classification network inside the discriminator network.
no code implementations • 25 Jul 2016 • Yaroslav Ganin, Daniil Kononenko, Diana Sungatullina, Victor Lempitsky
In this work, we consider the task of generating highly-realistic images of a given face with a redirected gaze.