I am a PhD student at Skoltech in computer vision group. My supervisors are Victor Lempitsky and Andrea Vedaldi. I also work for Yandex Research.

Selected publications

Adversarial Generator-Encoder Networks

Dmitry Ulyanov, Andrea Vedaldi, Victor Lempitsky


We present a new autoencoder-type architecture, that is trainable in an unsupervised mode, sustains both generation and inference, and has the quality of conditional and unconditional samples boosted by adversarial learning.

[paper] [code]

Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis

Dmitry Ulyanov, Andrea Vedaldi, Victor Lempitsky

CVPR 2017

We introduce Instance Normalization for a better stylization and derive entropy loss which improves samples diversity for both texture synthesis and stylization.

[paper] [code] [supplementary] [poster] [bibtex]

Texture Networks: Feed-forward Synthesis of Textures and Stylized Images

Dmitry Ulyanov, Vadim Lebedev, Andrea Vedaldi, Victor Lempitsky

ICML 2016

We speed up texture synthesis and famous neural style transfer of Gatys et al. by 500 times. The method was used by such stylization apps like Prisma and Vinci.

[paper] [code] [supplementary] [slides] [poster] [bibtex]


Multicore t-SNE

A multicore modification of L. Van der Maaten's Barnes-Hut t-SNE with python and Torch CFFI-based wrappers. The code also works faster than sklearn.TSNE on 1 core.


Online Neural Doodle

"Fast neural doodle" + "Texture Nets" = "Online neural doodle". Feed-forward generator allows real-time applications so we've built a web demo likeMonet.

[blog post] [code] [online demo]

Fast Neural Doodle

Neural doodle using gram matrices matching as opposed to original patch-based method.